Syracuse University
AI Insights
- The framework's performance may be affected by the quality of input data and the complexity of the query. (ML: 0.95)
- The benchmark evaluation only considers a limited set of intelligence modes, which may not fully represent the range of possible designs. (ML: 0.93)
- Agentic AI: An artificial intelligence that can act on behalf of humans to achieve specific goals. (ML: 0.91)
- Previous studies have shown that agentic AI can improve building energy management through optimized control policies and coordinated control strategies. (ML: 0.85)
- The benchmark evaluation highlights the importance of intelligence mode design in achieving balanced performance, with centralized two-stage mode providing the most reliable results while maintaining low execution latency and inference cost. (ML: 0.85)
- The results show the impact of system upgrades on thermal and electrical domain performance. (ML: 0.83)
- The proposed agentic AI framework demonstrates its ability to execute complex building energy management queries through sequential simulations. (ML: 0.81)
- The proposed agentic AI framework executes a realistic building energy management query through three sequential simulations: baseline configuration, system upgrade, and system upgrade with control upgrade. (ML: 0.78)
- MCP (Model-Component Platform): A platform for integrating models and components. (ML: 0.76)
- DER (Distributed Energy Resources): Devices or systems that generate, store, or manage energy locally. (ML: 0.75)
- PIML (Physical Information Modeling Language): A tool for modeling and simulating physical systems. (ML: 0.61)
Abstract
The urgent need for building decarbonization calls for a paradigm shift in future autonomous building energy operation, from human-intensive engineering workflows toward intelligent agents that interact with physics-grounded digital environments. This study proposes an end-to-end agentic AI-enabled Physics-Informed Machine Learning (PIML) environment for scalable building energy modeling, simulation, control, and automation. The framework consists of (1) a modular and physics-consistent PIML digital environment spanning building thermal dynamics, Heating, Ventilation, and Air Conditioning (HVAC), and distributed energy resources (DER) for grid-interactive energy management; and (2) an agentic AI layer with 11 specialist agents and 72 Model Context Protocol (MCP) tools that enable end-to-end execution of multi-step energy analytics. A representative case study demonstrates multi-domain, multi-agent coordination for assessing how system and control upgrades affect energy use, operating cost, thermal comfort, and flexibility. In addition, a large-scale benchmark (about 4000 runs) systematically evaluates workflow performance in terms of accuracy, token consumption, execution time, and inference cost. The results quantify the impacts of intelligence mode design, model size, task complexity, and orchestrator-specialist coordination, and provide key lessons for building future agentic AI systems in real-world building energy applications. This work establishes a scalable, physics-grounded foundation for deploying agentic AI in decarbonized and grid-interactive building operations.
The urgent need for building decarbonization calls for a paradigm shift in future autonomous building energy operation, from human-intensive engineering workflows toward intelligent agents that interact with physics-grounded digital environments. This study proposes an end-to-end agentic AI-enabled Physics-Informed Machine Learning (PIML) environment for scalable building energy modeling, simulation, control, and automation. The framework consists of (1) a modular and physics-consistent PIML digital environment spanning building thermal dynamics, Heating, Ventilation, and Air Conditioning (HVAC), and distributed energy resources (DER) for grid-interactive energy management; and (2) an agentic AI layer with 11 specialist agents and 72 Model Context Protocol (MCP) tools that enable end-to-end execution of multi-step energy analytics. A representative case study demonstrates multi-domain, multi-agent coordination for assessing how system and control upgrades affect energy use, operating cost, thermal comfort, and flexibility. In addition, a large-scale benchmark (about 4000 runs) systematically evaluates workflow performance in terms of accuracy, token consumption, execution time, and inference cost. The results quantify the impacts of intelligence mode design, model size, task complexity, and orchestrator-specialist coordination, and provide key lessons for building future agentic AI systems in real-world building energy applications. This work establishes a scalable, physics-grounded foundation for deploying agentic AI in decarbonized and grid-interactive building operations.
Why we are recommending this paper?
Because agi: artificial general intelligence is a popular topic and you have less than 3 interests with available recommendations
This paper focuses on intelligent agents for building operations, aligning with the user's interest in database systems and data warehousing through an agentic AI framework. The application to building decarbonization demonstrates a practical use case within a relevant domain.
Because agi: artificial general intelligence is a popular topic and you have less than 3 interests with available recommendations
This paper focuses on intelligent agents for building operations, aligning with the user's interest in database systems and data warehousing through an agentic AI framework. The application to building decarbonization demonstrates a practical use case within a relevant domain.
BITS Pilani KK Birla Goa Campus
AI Insights
- Domain-specific knowledge facilitates improving the performance of the DB-Routing task by providing additional semantic context to route queries. (ML: 0.95)
- DB-Routing: Routing end user queries to databases for answerability Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task Qwen2: A technical report on a family of highly capable multimodal models The proposed method provides a good solution for the DB-Routing task, with βΌ80% of queries having 100% Recall@1. (ML: 0.91)
- The proposed method consistently outperforms embedding-only and direct LLM-based baselines in challenging database scenarios. (ML: 0.91)
- The remaining 9% and 5% failed queries of Spider-Route and Bird-Route are ambiguous, where the top ranked DB by our method is also a valid DB to answer the query along with the ground truth DB. (ML: 0.91)
- Domain-specific knowledge provides additional semantic context to route queries in scenarios where DDL script of the schema alone cannot provide sufficient context to resolve them. (ML: 0.91)
- Decomposing query routing into interpretable and verifiable sub-tasks is crucial for building accurate, scalable, and reliable enterprise DB routing systems. (ML: 0.88)
- The proposed method still has 20% and 21% queries in Spider-Route and Bird-Route that do not have 100% Recall@1. (ML: 0.88)
Abstract
We address the task of routing natural language queries in multi-database enterprise environments. We construct realistic benchmarks by extending existing NL-to-SQL datasets. Our study shows that routing becomes increasingly challenging with larger, domain-overlapping DB repositories and ambiguous queries, motivating the need for more structured and robust reasoning-based solutions. By explicitly modelling schema coverage, structural connectivity, and fine-grained semantic alignment, the proposed modular, reasoning-driven reranking strategy consistently outperforms embedding-only and direct LLM-prompting baselines across all the metrics.
We address the task of routing natural language queries in multi-database enterprise environments. We construct realistic benchmarks by extending existing NL-to-SQL datasets. Our study shows that routing becomes increasingly challenging with larger, domain-overlapping DB repositories and ambiguous queries, motivating the need for more structured and robust reasoning-based solutions. By explicitly modelling schema coverage, structural connectivity, and fine-grained semantic alignment, the proposed modular, reasoning-driven reranking strategy consistently outperforms embedding-only and direct LLM-prompting baselines across all the metrics.
Why we are recommending this paper?
Due to your Interest in NoSQL Databases
This research directly addresses routing natural language queries to databases, a core component of NoSQL and SQL database design. The benchmark construction for enterprise environments is particularly relevant to the user's interests.
Due to your Interest in NoSQL Databases
This research directly addresses routing natural language queries to databases, a core component of NoSQL and SQL database design. The benchmark construction for enterprise environments is particularly relevant to the user's interests.
xbenchai
AI Insights
- The results highlight the need for further research in instruction-following tasks and the development of more effective language models. (ML: 0.98)
- The authors acknowledge that the proposed benchmark may not capture all aspects of real-world instruction-following tasks. (ML: 0.98)
- The synthetic data generation approach relies on human-made questions and may not accurately reflect real-world scenarios. (ML: 0.96)
- The paper proposes a new benchmark for evaluating the ability of language models to follow complex instructions and perform tasks that require multiple steps. (ML: 0.96)
- The proposed benchmark provides a more comprehensive evaluation of language models' ability to follow instructions and perform tasks. (ML: 0.96)
- Synthetic data generation: The process of creating artificial data that mimics real-world scenarios, used to train and evaluate language models. (ML: 0.96)
- The results show that state-of-the-art language models struggle to perform well on this benchmark, highlighting the need for more research in this area. (ML: 0.95)
- The authors introduce a novel approach to generating synthetic data for instruction-following tasks, which allows them to create a large-scale dataset with diverse and realistic scenarios. (ML: 0.94)
- Instruction-following task: A task that requires a model to follow a set of instructions to complete a specific goal or achieve a certain outcome. (ML: 0.93)
- The synthetic data generation approach allows for the creation of diverse and realistic scenarios, making it easier to train and evaluate language models. (ML: 0.93)
Abstract
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.
Why we are recommending this paper?
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
The paper's focus on AI agents handling complex tasks aligns with the user's interest in database design and data warehousing, particularly as it relates to more sophisticated data processing.
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
The paper's focus on AI agents handling complex tasks aligns with the user's interest in database design and data warehousing, particularly as it relates to more sophisticated data processing.
NYU Grossman School of Medicine
AI Insights
- The dataset includes images of skin lesions, which are annotated with labels indicating the type of lesion and its severity. (ML: 0.94)
- The dataset can be used for training machine learning models to diagnose skin conditions from images. (ML: 0.91)
- Digital pathology: The practice of using digital tools and techniques to analyze and interpret histopathological images. (ML: 0.91)
- The dataset is available for download and use by researchers and clinicians. (ML: 0.91)
- The preprocessed dataset ensures that patient privacy is maintained while still allowing for meaningful analysis and annotation. (ML: 0.90)
- The dataset is a valuable resource for researchers and clinicians working in the field of dermatopathology. (ML: 0.90)
- The dataset has been preprocessed to remove identifying information and ensure patient privacy. (ML: 0.89)
- The dataset is a collection of images from various sources, including publicly available datasets and private collections. (ML: 0.86)
- De-identification: The process of removing identifying information from medical images to ensure patient privacy. (ML: 0.84)
- Whole-slide imaging (WSI): A technique that captures high-resolution images of entire slides, allowing for detailed analysis and annotation. (ML: 0.80)
Abstract
Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and dermatopathology trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6\% for the deep learning approach, 61.0\% for the keyword-based retrieval method, and 90.4\% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.
Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and dermatopathology trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6\% for the deep learning approach, 61.0\% for the keyword-based retrieval method, and 90.4\% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.
Why we are recommending this paper?
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
This paper explores the use of AI in dermatopathology, a field reliant on database management and data analysis for diagnosis and research. It's a specialized application of database principles.
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
This paper explores the use of AI in dermatopathology, a field reliant on database management and data analysis for diagnosis and research. It's a specialized application of database principles.
Radboud University
AI Insights
- Value-Sensitive Design (VSD) can help the community reflect on how genAI tools affect learning, expertise development, and knowledge passing, and make choices about tools, incentives, and evaluation practices with explicit attention to agency, responsibility, and learning. (ML: 0.99)
- The community should support practices that preserve technical grounding, encourage verification, and maintain human responsibility, rather than relying solely on efficiency and automation. (ML: 0.98)
- Researchers are losing technical grounding and becoming dependent on automated systems, which can lead to errors and accountability issues. (ML: 0.98)
- A renewed emphasis on first-principles thinking, verification literacy, and resilience in research practice is necessary to ensure that researchers remain responsible for their outputs and capable of intervening when AI tools fail. (ML: 0.98)
- The software engineering research community must prioritize human responsibility and accountability in the face of widespread AI assistance. (ML: 0.98)
- Resilience in Research Practice: The capacity to reason about and solve problems without continuous reliance on automated systems. (ML: 0.97)
- Value-Sensitive Design (VSD): A research and design approach that explicitly accounts for human values throughout the design, development, and use of technology. (ML: 0.97)
- Verification Literacy: The ability to audit and test AI-generated outputs in a rigorous way, requiring deeper technical understanding. (ML: 0.97)
- The software engineering research community is at a crossroads as AI-based tools become more prevalent in their work. (ML: 0.96)
- Design Fiction: A narrative technique used to explore the implications of emerging technologies on society. (ML: 0.92)
Abstract
Rising publication pressure and the routine use of generative AI tools are reshaping how software engineering research is produced, assessed, and taught. While these developments promise efficiency, they also raise concerns about skill degradation, responsibility, and trust in scholarly outputs. This vision paper employs Design Fiction as a methodological lens to examine how such concerns might materialise if current practices persist. Drawing on themes reported in a recent community survey, we construct a speculative artifact situated in a near future research setting. The fiction is used as an analytical device rather than a forecast, enabling reflection on how automated assistance might impede domain knowledge competence, verification, and mentoring practices. By presenting an intentionally unsettling scenario, the paper invites discussion on how the software engineering research community in the future will define proficiency, allocate responsibility, and support learning.
Rising publication pressure and the routine use of generative AI tools are reshaping how software engineering research is produced, assessed, and taught. While these developments promise efficiency, they also raise concerns about skill degradation, responsibility, and trust in scholarly outputs. This vision paper employs Design Fiction as a methodological lens to examine how such concerns might materialise if current practices persist. Drawing on themes reported in a recent community survey, we construct a speculative artifact situated in a near future research setting. The fiction is used as an analytical device rather than a forecast, enabling reflection on how automated assistance might impede domain knowledge competence, verification, and mentoring practices. By presenting an intentionally unsettling scenario, the paper invites discussion on how the software engineering research community in the future will define proficiency, allocate responsibility, and support learning.
Why we are recommending this paper?
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
This paper examines the impact of AI on software engineering research, directly touching on the user's interest in database design and the evolving landscape of research methodologies.
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
This paper examines the impact of AI on software engineering research, directly touching on the user's interest in database design and the evolving landscape of research methodologies.
University of WisconsinMadison
AI Insights
- A generic workflow for EduDB's benchmark has been introduced to evaluate and rank students' optimizations. (ML: 0.93)
- EduDB: A simple database prototype designed for educational purposes. (ML: 0.92)
- Parser: The component responsible for parsing SQL queries into an abstract syntax tree (AST). (ML: 0.92)
- EduDB is a simple database prototype designed for educational purposes. (ML: 0.91)
- The system consists of several components, including the parser, query executor, buffer manager, file manager, concurrency manager, and transaction manager. (ML: 0.89)
- Query Executor: The component that executes the parsed query on the database. (ML: 0.84)
- File Manager: Responsible for managing files and directories on disk. (ML: 0.81)
- Buffer Manager: Manages the buffer cache, which stores frequently accessed data in memory. (ML: 0.80)
- Concurrency Manager: Ensures that multiple transactions can be executed concurrently without conflicts. (ML: 0.79)
- Transaction Manager: Manages the execution of transactions, including commit and rollback operations. (ML: 0.76)
Abstract
Database Management System (DBMS) is designed to help store and process large collections of data, and is incredibly flexible to perform various kinds of optimizations as long as it achieves serializability with a high-level interface available. The current undergraduate level DBMS course in UW-Madison (i.e., CS564) involves implementing specific modules of DB architecture, including B+ tree, but students may end up spending numerous amounts of effort on corner cases and not gaining a more comprehensive understanding of the internal design. Thus, we present EduDB, a simple database prototype for educational purposes that provides students a clean, concise, and comprehensive overview of the database system. We also attempt to develop an integrative series of course projects based on EduDB, which offers a platform for students to perform any optimization learned during the semester.
Database Management System (DBMS) is designed to help store and process large collections of data, and is incredibly flexible to perform various kinds of optimizations as long as it achieves serializability with a high-level interface available. The current undergraduate level DBMS course in UW-Madison (i.e., CS564) involves implementing specific modules of DB architecture, including B+ tree, but students may end up spending numerous amounts of effort on corner cases and not gaining a more comprehensive understanding of the internal design. Thus, we present EduDB, a simple database prototype for educational purposes that provides students a clean, concise, and comprehensive overview of the database system. We also attempt to develop an integrative series of course projects based on EduDB, which offers a platform for students to perform any optimization learned during the semester.
Why we are recommending this paper?
Due to your Interest in Relational Databases
Due to your Interest in Relational Databases
University of Notre Dame
AI Insights
- Participants may have had prior experience with computer science concepts, which could influence their performance in the study. (ML: 0.99)
- The study suggests that providing multiple representations can support the learning of data structures by BVI individuals, but it is essential to consider individual differences in learning styles and preferences. (ML: 0.98)
- The study found that BVI individuals use multiple representations to understand and reason about data structures in a way that is consistent with sighted individuals, but they may require more time and practice to develop their skills. (ML: 0.98)
- The study aimed to investigate how blind or visually impaired (BVI) individuals use multiple representations to understand and reason about data structures, specifically arrays and binary trees. (ML: 0.96)
- The participants used the tabular representation most frequently for arrays, while the navigable representation was preferred for binary trees. (ML: 0.95)
- Data Structure: A way of organizing and storing data in a computer so that it can be efficiently accessed and modified. (ML: 0.94)
- Limited sample size of 8 participants. (ML: 0.93)
- Binary Tree: A hierarchical structure where each node has at most two children (left child and right child). (ML: 0.85)
- Array: A linear collection of elements, each identified by an index. (ML: 0.82)
- Blind or Visually Impaired (BVI): Individuals who are unable to see or have limited vision. (ML: 0.77)
Abstract
Blind and visually impaired (BVI) computer science students face systematic barriers when learning data structures: current accessibility approaches typically translate diagrams into alternative text, focusing on visual appearance rather than preserving the underlying structure essential for conceptual understanding. More accessible alternatives often do not scale in complexity, cost to produce, or both. Motivated by a recent shift to tools for creating visual diagrams from code, we propose a solution that automatically creates accessible representations from structural information about diagrams. Based on a Wizard-of-Oz study, we derive design requirements for an automated system, Arboretum, that compiles text-based diagram specifications into three synchronized nonvisual formats$\unicode{x2013}$tabular, navigable, and tactile. Our evaluation with BVI users highlights the strength of tactile graphics for complex tasks such as binary search; the benefits of offering multiple, complementary nonvisual representations; and limitations of existing digital navigation patterns for structural reasoning. This work reframes access to data structures by preserving their structural properties. The solution is a practical system to advance accessible CS education.
Blind and visually impaired (BVI) computer science students face systematic barriers when learning data structures: current accessibility approaches typically translate diagrams into alternative text, focusing on visual appearance rather than preserving the underlying structure essential for conceptual understanding. More accessible alternatives often do not scale in complexity, cost to produce, or both. Motivated by a recent shift to tools for creating visual diagrams from code, we propose a solution that automatically creates accessible representations from structural information about diagrams. Based on a Wizard-of-Oz study, we derive design requirements for an automated system, Arboretum, that compiles text-based diagram specifications into three synchronized nonvisual formats$\unicode{x2013}$tabular, navigable, and tactile. Our evaluation with BVI users highlights the strength of tactile graphics for complex tasks such as binary search; the benefits of offering multiple, complementary nonvisual representations; and limitations of existing digital navigation patterns for structural reasoning. This work reframes access to data structures by preserving their structural properties. The solution is a practical system to advance accessible CS education.
Why we are recommending this paper?
Due to your Interest in Data Warehousing
Due to your Interest in Data Warehousing
Amazon
AI Insights
- It's like having a personal assistant who helps you make data-driven decisions. (ML: 0.97)
- The paper introduces Insight Agents (IA), a hierarchical multi-agent system leveraging Large Language Models (LLMs) built on a plan-and-execute paradigm to provide personalized, actionable insights for e-commerce sellers. (ML: 0.96)
- Insight Agents (IA) Large Language Models (LLMs) plan-and-execute paradigm IA sets the stage for future AI-driven decision supporting systems, transforming data interaction and driving impactful outcomes in e-commerce and beyond. (ML: 0.96)
- The system may not be able to handle complex or nuanced queries. (ML: 0.95)
- Insight Agents (IA) is a system that uses Large Language Models (LLMs) to provide personalized and actionable insights. (ML: 0.94)
- Insight Agents (IA) is a hierarchical multi-agent system leveraging Large Language Models (LLMs) built on a plan-and-execute paradigm to provide personalized, actionable insights for e-commerce sellers. (ML: 0.94)
- Imagine you're an e-commerce seller, and you want to get insights about your sales. (ML: 0.92)
- The system significantly reduces cognitive load, achieving 89.5% accuracy with sub-15-second latency. (ML: 0.88)
- The paper cites several studies on LLMs and their applications in various domains. (ML: 0.86)
Abstract
Today, E-commerce sellers face several key challenges, including difficulties in discovering and effectively utilizing available programs and tools, and struggling to understand and utilize rich data from various tools. We therefore aim to develop Insight Agents (IA), a conversational multi-agent Data Insight system, to provide E-commerce sellers with personalized data and business insights through automated information retrieval. Our hypothesis is that IA will serve as a force multiplier for sellers, thereby driving incremental seller adoption by reducing the effort required and increase speed at which sellers make good business decisions. In this paper, we introduce this novel LLM-backed end-to-end agentic system built on a plan-and-execute paradigm and designed for comprehensive coverage, high accuracy, and low latency. It features a hierarchical multi-agent structure, consisting of manager agent and two worker agents: data presentation and insight generation, for efficient information retrieval and problem-solving. We design a simple yet effective ML solution for manager agent that combines Out-of-Domain (OOD) detection using a lightweight encoder-decoder model and agent routing through a BERT-based classifier, optimizing both accuracy and latency. Within the two worker agents, a strategic planning is designed for API-based data model that breaks down queries into granular components to generate more accurate responses, and domain knowledge is dynamically injected to to enhance the insight generator. IA has been launched for Amazon sellers in US, which has achieved high accuracy of 90% based on human evaluation, with latency of P90 below 15s.
Today, E-commerce sellers face several key challenges, including difficulties in discovering and effectively utilizing available programs and tools, and struggling to understand and utilize rich data from various tools. We therefore aim to develop Insight Agents (IA), a conversational multi-agent Data Insight system, to provide E-commerce sellers with personalized data and business insights through automated information retrieval. Our hypothesis is that IA will serve as a force multiplier for sellers, thereby driving incremental seller adoption by reducing the effort required and increase speed at which sellers make good business decisions. In this paper, we introduce this novel LLM-backed end-to-end agentic system built on a plan-and-execute paradigm and designed for comprehensive coverage, high accuracy, and low latency. It features a hierarchical multi-agent structure, consisting of manager agent and two worker agents: data presentation and insight generation, for efficient information retrieval and problem-solving. We design a simple yet effective ML solution for manager agent that combines Out-of-Domain (OOD) detection using a lightweight encoder-decoder model and agent routing through a BERT-based classifier, optimizing both accuracy and latency. Within the two worker agents, a strategic planning is designed for API-based data model that breaks down queries into granular components to generate more accurate responses, and domain knowledge is dynamically injected to to enhance the insight generator. IA has been launched for Amazon sellers in US, which has achieved high accuracy of 90% based on human evaluation, with latency of P90 below 15s.
Why we are recommending this paper?
Due to your Interest in Data Warehousing
Due to your Interest in Data Warehousing
University of Tartu
AI Insights
- It emphasizes the need for a more comprehensive understanding of the complex relationships between technological, social, and economic factors in AI development and deployment. (ML: 0.99)
- It cites studies on AI bias, transparency, accountability, and the need for responsible AI development and deployment. (ML: 0.99)
- The study acknowledges that it has limitations due to the complexity of the topic and the need for further research. (ML: 0.98)
- It also recognizes that the development of AI governance frameworks is a dynamic process that requires ongoing evaluation and refinement. (ML: 0.98)
- The study highlights the importance of considering paradoxes when developing AI governance frameworks. (ML: 0.97)
- The paper explores these kinds of complexities in AI governance and why they need to be considered when developing frameworks for responsible AI development and deployment. (ML: 0.97)
- The paper explores the concept of paradox in the context of artificial intelligence (AI) and its governance, highlighting the importance of considering these complexities when developing AI governance frameworks. (ML: 0.97)
- The paper discusses the concept of paradox in management and organization theories, specifically focusing on artificial intelligence (AI) and its governance. (ML: 0.96)
- The paper draws on existing literature in management, organization theory, and AI ethics to inform its discussion of paradoxes in AI governance. (ML: 0.95)
- Imagine you're trying to create a system that can make decisions without being biased, but at the same time, you want it to be transparent so people understand how those decisions are made. (ML: 0.93)
- That's a paradox! (ML: 0.91)
- Paradox: a situation or condition that is contradictory or opposite to what would be expected. (ML: 0.86)
Abstract
The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.
The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.
Why we are recommending this paper?
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
University of Bochum
AI Insights
- The concept of human-centered AI may be challenging to implement in organizations with rigid structures or cultures. (ML: 0.98)
- Collaboration between experts, 7. (ML: 0.98)
- Human-centered AI may not be suitable for all types of tasks or industries, requiring careful consideration and evaluation. (ML: 0.98)
- Continuous learning and improvement, 2. (ML: 0.98)
- Monitoring and evaluation, and 10. (ML: 0.97)
- Clear roles and responsibilities, 5. (ML: 0.97)
- Effective communication, 6. (ML: 0.96)
- The concept of keeping the organization in the loop is crucial for the successful implementation of human-centered AI. (ML: 0.96)
- Interacting organizational practices require significant resources and effort to establish and maintain. (ML: 0.96)
- Ten types of interacting organizational practices are identified as essential to accompany human-centered AI: 1. (ML: 0.96)
- Case B substantiates this concept by highlighting the collaboration between technical and analytical experts, anchored in systematic communication structures. (ML: 0.96)
- Interacting organizational practices are essential to accompany human-centered AI and ensure its effectiveness and adaptability. (ML: 0.95)
- Adaptation processes, 8. (ML: 0.95)
- Human-centered AI: An approach to keeping the human in the loop by emphasizing the importance of interacting organizational practices. (ML: 0.95)
- The concept of keeping the organization in the loop is developed based on case A, which emphasizes the importance of human-centered AI and the need for interacting organizational practices. (ML: 0.95)
- Interacting organizational practices: The essential types of practices that need to accompany human-centered AI, including continuous learning and improvement, feedback mechanisms, regular meetings and updates, clear roles and responsibilities, effective communication, collaboration between experts, adaptation processes, documentation and knowledge management, monitoring and evaluation, and continuous refinement of the AI system. (ML: 0.94)
- Feedback mechanisms, 3. (ML: 0.93)
- Continuous refinement of the AI system. (ML: 0.91)
- Documentation and knowledge management, 9. (ML: 0.89)
- Regular meetings and updates, 4. (ML: 0.89)
Abstract
This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical perspective to comply with the requirements of Human-centered AI (HCAI). Instead of viewing AI merely as a technical tool, the analysis emphasizes the importance of embedding AI into communication, collaboration, and decision-making processes within organizations from a human-centered perspective. Ten case-based patterns illustrate how AI support of predictive maintenance can be organized to address quality assurance and continuous improvement and to provide different types of sup-port for HCAI. The analysis shows that AI adoption often requires and enables new forms of organizational learning, where specialists jointly interpret AI output, adapt workflows, and refine rules for system improve-ment. Different dimensions and levels of socio-technical integration of AI are considered to reflect the effort and benefits of keeping the organization in the loop.
This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical perspective to comply with the requirements of Human-centered AI (HCAI). Instead of viewing AI merely as a technical tool, the analysis emphasizes the importance of embedding AI into communication, collaboration, and decision-making processes within organizations from a human-centered perspective. Ten case-based patterns illustrate how AI support of predictive maintenance can be organized to address quality assurance and continuous improvement and to provide different types of sup-port for HCAI. The analysis shows that AI adoption often requires and enables new forms of organizational learning, where specialists jointly interpret AI output, adapt workflows, and refine rules for system improve-ment. Different dimensions and levels of socio-technical integration of AI are considered to reflect the effort and benefits of keeping the organization in the loop.
Why we are recommending this paper?
Because ai and society is a popular topic and you have less than 3 interests with available recommendations
Because ai and society is a popular topic and you have less than 3 interests with available recommendations
Universit Paris Cit , CNRS
AI Insights
- The authors show that any feedforward network with ReLU activations can be viewed as a place-independent IFS, and they extend this result to other types of neural networks, including residual blocks and MoE models. (ML: 0.92)
- The paper discusses the interpretation of deep neural networks as iterated function systems (IFSs) and provides a general framework for analyzing their convergence properties. (ML: 0.89)
- The paper provides several examples of neural network architectures that can be interpreted as IFSs, including ResNet with Softplus activation, Transformer block, and MoE model. (ML: 0.88)
- The authors use the Hutchinson operator to analyze the convergence properties of IFSs and show that they can be used to bound the Wasserstein distance between the output of a neural network and its fixed point. (ML: 0.87)
- Definition 1: A Markov recursion is a sequence of random variables {Xn} defined by X0 = x and Xt+1 = w(Xt, Ξ), where w is a function that depends on the current state Xt and the parameter Ξ. (ML: 0.82)
- Definition 3: A place-dependent IFS (P-IFS) is an IFS {wΞΎ} where each wΞΎ depends on the current state x and the parameter Ξ. (ML: 0.80)
- Definition 2: An iterated function system (IFS) is a collection of functions {wΞΎ} indexed by ΞΎ β I, where each wΞΎ is a Lipschitz map from X to itself. (ML: 0.80)
- They also introduce the concept of strong average Lipschitz contractivity for place-dependent IFSs and provide conditions under which it holds. (ML: 0.75)
- Definition 5: A P-IFS {wΞΎ} is strongly average-contractive if sup_xβX β_{ΞΎβI} pΞΎ(x)cΞΎ β€ c < 1. (ML: 0.67)
- Definition 4: The Hutchinson operator T is a contraction on the space of probability measures PP(X) with respect to the Wasserstein distance W2 if there exists a constant c < 1 such that W2(T(Β΅), T(Ξ½)) β€ cW2(Β΅, Ξ½) for all Β΅, Ξ½ β PP(X). (ML: 0.67)
- The Hutchinson operator T is defined as T(Β΅) = β_{ΞΎβI} pwΞΎ#Β΅q. (ML: 0.49)
Abstract
Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of parametrized functions, a mechanism that can be unstable and difficult to train, making stability a primary concern. Even when training succeeds, there are few rigorous results on how well such models generalize beyond the observed data, especially in the generative setting. In this work, we leverage the theory of stochastic Iterated Function Systems (IFS) and show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS. This connection allows us to import results from random dynamical systems to (i) establish the existence and uniqueness of invariant measures under suitable contractivity assumptions, and (ii) derive a Wasserstein generalization bound for generative modeling. The bound naturally leads to a new training objective that directly controls the collage-type approximation error between the data distribution and its image under the learned transfer operator. We illustrate the theory on a controlled 2D example and empirically evaluate the proposed objective on standard image datasets (MNIST, CelebA, CIFAR-10).
Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of parametrized functions, a mechanism that can be unstable and difficult to train, making stability a primary concern. Even when training succeeds, there are few rigorous results on how well such models generalize beyond the observed data, especially in the generative setting. In this work, we leverage the theory of stochastic Iterated Function Systems (IFS) and show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS. This connection allows us to import results from random dynamical systems to (i) establish the existence and uniqueness of invariant measures under suitable contractivity assumptions, and (ii) derive a Wasserstein generalization bound for generative modeling. The bound naturally leads to a new training objective that directly controls the collage-type approximation error between the data distribution and its image under the learned transfer operator. We illustrate the theory on a controlled 2D example and empirically evaluate the proposed objective on standard image datasets (MNIST, CelebA, CIFAR-10).
Why we are recommending this paper?
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Harvard University
AI Insights
- Milestones serve dual pedagogical and validation purposes, providing motivation through historical framing and demonstrating implementation correctness through real-world task performance. (ML: 0.98)
- Each module concludes with systems reasoning prompts measuring conceptual understanding beyond syntactic correctness. (ML: 0.97)
- Milestones are designed to be challenging but achievable, allowing students to demonstrate their understanding of complex concepts through real-world tasks. (ML: 0.96)
- Assessment validates both isolated correctness and cross-module integration. (ML: 0.96)
- The TinyTorch framework is designed for teaching machine learning concepts through hands-on implementation and analysis. (ML: 0.95)
- Reflect: Systems Analysis Questions. (ML: 0.94)
- TinyTorch follows a consistent Build-Use-Reflect cycle, integrating implementation, application, and systems reasoning to address multiple learning objectives. (ML: 0.94)
- It's a pedagogical tool aimed at bridging the gap between theoretical understanding and practical application. (ML: 0.94)
- Students implement components in Jupyter notebooks with scaffolded guidance. (ML: 0.91)
- TinyTorch's design emphasizes systems thinking, encouraging students to analyze and understand the relationships between components, rather than just focusing on individual functions. (ML: 0.87)
- The framework includes six historical milestones that recreate actual breakthroughs using exclusively student code, validating success through task-appropriate performance. (ML: 0.85)
- The framework is built with a focus on explicit dependencies, making it easier for students to understand where each module fits in the larger architecture. (ML: 0.83)
- Use: Integration Testing Beyond Unit Tests. (ML: 0.77)
- Build: Implementation with Explicit Dependencies. (ML: 0.66)
Abstract
Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling, optimizer theory without knowing why Adam requires 3x the memory of SGD. This "algorithm-systems divide" produces practitioners who can train models but cannot debug memory failures, optimize inference latency, or reason about deployment trade-offs--the very skills industry demands as "ML systems engineering." We present TinyTorch, a 20-module curriculum that closes this gap through "implementation-based systems pedagogy": students construct PyTorch's core components (tensors, autograd, optimizers, CNNs, transformers) in pure Python, building a complete framework where every operation they invoke is code they wrote. The design employs three patterns: "progressive disclosure" of complexity, "systems-first integration" of profiling from the first module, and "build-to-validate milestones" recreating 67 years of ML breakthroughs--from Perceptron (1958) through Transformers (2017) to MLPerf-style benchmarking. Requiring only 4GB RAM and no GPU, TinyTorch demonstrates that deep ML systems understanding is achievable without specialized hardware. The curriculum is available open-source at mlsysbook.ai/tinytorch.
Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling, optimizer theory without knowing why Adam requires 3x the memory of SGD. This "algorithm-systems divide" produces practitioners who can train models but cannot debug memory failures, optimize inference latency, or reason about deployment trade-offs--the very skills industry demands as "ML systems engineering." We present TinyTorch, a 20-module curriculum that closes this gap through "implementation-based systems pedagogy": students construct PyTorch's core components (tensors, autograd, optimizers, CNNs, transformers) in pure Python, building a complete framework where every operation they invoke is code they wrote. The design employs three patterns: "progressive disclosure" of complexity, "systems-first integration" of profiling from the first module, and "build-to-validate milestones" recreating 67 years of ML breakthroughs--from Perceptron (1958) through Transformers (2017) to MLPerf-style benchmarking. Requiring only 4GB RAM and no GPU, TinyTorch demonstrates that deep ML systems understanding is achievable without specialized hardware. The curriculum is available open-source at mlsysbook.ai/tinytorch.
Why we are recommending this paper?
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Southeast University
AI Insights
- Artifact-aware evaluation framework: A comprehensive framework for evaluating video generation models based on their ability to detect and correct artifacts. (ML: 0.94)
- The proposed framework provides a comprehensive evaluation of video generation models, enabling researchers to identify areas for improvement. (ML: 0.94)
- Video quality assessment methods: Techniques for evaluating the quality of generated videos based on various metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). (ML: 0.93)
- The novel DV AR (Dense Video Artifact Recognition) framework is proposed, which leverages the strengths of both text-to-video diffusion models and video quality assessment methods. (ML: 0.91)
- The paper proposes a comprehensive artifact-aware evaluation framework for video generation, focusing on fine-grained artifact detection across Appearance, Motion, and Camera dimensions. (ML: 0.91)
- Experimental results demonstrate the accuracy of the approach in identifying artifacts in generated videos, with a significant improvement over state-of-the-art methods. (ML: 0.90)
- Text-to-video diffusion models: A type of deep learning model that generates videos from text descriptions. (ML: 0.88)
- Fine-grained artifact detection: The process of detecting specific types of artifacts in videos, such as noise, blurriness, or color distortion. (ML: 0.87)
- The large-scale GenVID dataset is introduced, which includes a wide range of videos with diverse content, styles, and quality levels. (ML: 0.87)
- The FMG-DFS strategy enhances temporal localization, enabling more precise and efficient artifact detection. (ML: 0.68)
Abstract
With the rapid advancement of video generation techniques, evaluating and auditing generated videos has become increasingly crucial. Existing approaches typically offer coarse video quality scores, lacking detailed localization and categorization of specific artifacts. In this work, we introduce a comprehensive evaluation protocol focusing on three key aspects affecting human perception: Appearance, Motion, and Camera. We define these axes through a taxonomy of 10 prevalent artifact categories reflecting common generative failures observed in video generation. To enable robust artifact detection and categorization, we introduce GenVID, a large-scale dataset of 80k videos generated by various state-of-the-art video generation models, each carefully annotated for the defined artifact categories. Leveraging GenVID, we develop DVAR, a Dense Video Artifact Recognition framework for fine-grained identification and classification of generative artifacts. Extensive experiments show that our approach significantly improves artifact detection accuracy and enables effective filtering of low-quality content.
With the rapid advancement of video generation techniques, evaluating and auditing generated videos has become increasingly crucial. Existing approaches typically offer coarse video quality scores, lacking detailed localization and categorization of specific artifacts. In this work, we introduce a comprehensive evaluation protocol focusing on three key aspects affecting human perception: Appearance, Motion, and Camera. We define these axes through a taxonomy of 10 prevalent artifact categories reflecting common generative failures observed in video generation. To enable robust artifact detection and categorization, we introduce GenVID, a large-scale dataset of 80k videos generated by various state-of-the-art video generation models, each carefully annotated for the defined artifact categories. Leveraging GenVID, we develop DVAR, a Dense Video Artifact Recognition framework for fine-grained identification and classification of generative artifacts. Extensive experiments show that our approach significantly improves artifact detection accuracy and enables effective filtering of low-quality content.
Why we are recommending this paper?
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Rutgers University
AI Insights
- Generative models: A class of machine learning algorithms that can generate new data samples based on a given dataset. (ML: 0.97)
- The paper assumes that the input text is well-formed and does not contain any errors or ambiguities. (ML: 0.97)
- Diffusion prior constraints: A type of regularization technique used in generative models that encourages the model to produce samples that are similar to the data distribution. (ML: 0.92)
- The paper discusses the concept of ConceptLab, a creative generation system that uses diffusion prior constraints to generate novel images. (ML: 0.90)
- ConceptLab is based on a combination of generative models and text-image harmony, which allows it to produce high-quality images with specific styles and concepts. (ML: 0.88)
- ConceptLab is based on a combination of generative models and text-image harmony, which allows it to produce high-quality images with specific styles and concepts. (ML: 0.88)
- The paper presents ConceptLab, a creative generation system that uses diffusion prior constraints to generate novel images. (ML: 0.86)
- The authors propose a new method for training generative models using diffusion prior constraints, which enables the model to learn from the data distribution and generate novel samples. (ML: 0.84)
- The authors propose a new method for training generative models using diffusion prior constraints, which enables the model to learn from the data distribution and generate novel samples. (ML: 0.84)
- Text-image harmony: A method for combining text and image features to generate images with specific styles and concepts. (ML: 0.76)
Abstract
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative generation using diffusion models, where creativity is associated with the inverse probability of an image's existence in the CLIP embedding space. Unlike prior approaches that rely on a manual blending of concepts or exclusion of subcategories, our method calculates the probability distribution of generated images and drives it towards low-probability regions to produce rare, imaginative, and visually captivating outputs. We also introduce pullback mechanisms, achieving high creativity without sacrificing visual fidelity. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness and efficiency of our creative generation framework, showcasing its ability to produce unique, novel, and thought-provoking images. This work provides a new perspective on creativity in generative models, offering a principled method to foster innovation in visual content synthesis.
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative generation using diffusion models, where creativity is associated with the inverse probability of an image's existence in the CLIP embedding space. Unlike prior approaches that rely on a manual blending of concepts or exclusion of subcategories, our method calculates the probability distribution of generated images and drives it towards low-probability regions to produce rare, imaginative, and visually captivating outputs. We also introduce pullback mechanisms, achieving high creativity without sacrificing visual fidelity. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness and efficiency of our creative generation framework, showcasing its ability to produce unique, novel, and thought-provoking images. This work provides a new perspective on creativity in generative models, offering a principled method to foster innovation in visual content synthesis.
Why we are recommending this paper?
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
We did not find tons of content matching your interests we've included some additional topics that are popular. Also be aware that if the topics is not present in arxiv we wont be able to recommend it.
University of Tartu
AI Insights
- It emphasizes the need for a more comprehensive understanding of the complex relationships between technological, social, and economic factors in AI development and deployment. (ML: 0.99)
- It cites studies on AI bias, transparency, accountability, and the need for responsible AI development and deployment. (ML: 0.99)
- The study acknowledges that it has limitations due to the complexity of the topic and the need for further research. (ML: 0.98)
- It also recognizes that the development of AI governance frameworks is a dynamic process that requires ongoing evaluation and refinement. (ML: 0.98)
- The study highlights the importance of considering paradoxes when developing AI governance frameworks. (ML: 0.97)
- The paper explores these kinds of complexities in AI governance and why they need to be considered when developing frameworks for responsible AI development and deployment. (ML: 0.97)
- The paper explores the concept of paradox in the context of artificial intelligence (AI) and its governance, highlighting the importance of considering these complexities when developing AI governance frameworks. (ML: 0.97)
- The paper discusses the concept of paradox in management and organization theories, specifically focusing on artificial intelligence (AI) and its governance. (ML: 0.96)
- The paper draws on existing literature in management, organization theory, and AI ethics to inform its discussion of paradoxes in AI governance. (ML: 0.95)
- Imagine you're trying to create a system that can make decisions without being biased, but at the same time, you want it to be transparent so people understand how those decisions are made. (ML: 0.93)
- That's a paradox! (ML: 0.91)
- Paradox: a situation or condition that is contradictory or opposite to what would be expected. (ML: 0.86)
Abstract
The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.
The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.
Why we are recommending this paper?
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
xbenchai
AI Insights
- The results highlight the need for further research in instruction-following tasks and the development of more effective language models. (ML: 0.98)
- The authors acknowledge that the proposed benchmark may not capture all aspects of real-world instruction-following tasks. (ML: 0.98)
- The synthetic data generation approach relies on human-made questions and may not accurately reflect real-world scenarios. (ML: 0.96)
- The paper proposes a new benchmark for evaluating the ability of language models to follow complex instructions and perform tasks that require multiple steps. (ML: 0.96)
- The proposed benchmark provides a more comprehensive evaluation of language models' ability to follow instructions and perform tasks. (ML: 0.96)
- Synthetic data generation: The process of creating artificial data that mimics real-world scenarios, used to train and evaluate language models. (ML: 0.96)
- The results show that state-of-the-art language models struggle to perform well on this benchmark, highlighting the need for more research in this area. (ML: 0.95)
- The authors introduce a novel approach to generating synthetic data for instruction-following tasks, which allows them to create a large-scale dataset with diverse and realistic scenarios. (ML: 0.94)
- Instruction-following task: A task that requires a model to follow a set of instructions to complete a specific goal or achieve a certain outcome. (ML: 0.93)
- The synthetic data generation approach allows for the creation of diverse and realistic scenarios, making it easier to train and evaluate language models. (ML: 0.93)
Abstract
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.
Why we are recommending this paper?
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
Because ai agents is a popular topic and you have less than 3 interests with available recommendations
University of Bochum
AI Insights
- The concept of human-centered AI may be challenging to implement in organizations with rigid structures or cultures. (ML: 0.98)
- Collaboration between experts, 7. (ML: 0.98)
- Human-centered AI may not be suitable for all types of tasks or industries, requiring careful consideration and evaluation. (ML: 0.98)
- Continuous learning and improvement, 2. (ML: 0.98)
- Monitoring and evaluation, and 10. (ML: 0.97)
- Clear roles and responsibilities, 5. (ML: 0.97)
- Effective communication, 6. (ML: 0.96)
- The concept of keeping the organization in the loop is crucial for the successful implementation of human-centered AI. (ML: 0.96)
- Interacting organizational practices require significant resources and effort to establish and maintain. (ML: 0.96)
- Ten types of interacting organizational practices are identified as essential to accompany human-centered AI: 1. (ML: 0.96)
- Case B substantiates this concept by highlighting the collaboration between technical and analytical experts, anchored in systematic communication structures. (ML: 0.96)
- Interacting organizational practices are essential to accompany human-centered AI and ensure its effectiveness and adaptability. (ML: 0.95)
- Adaptation processes, 8. (ML: 0.95)
- Human-centered AI: An approach to keeping the human in the loop by emphasizing the importance of interacting organizational practices. (ML: 0.95)
- The concept of keeping the organization in the loop is developed based on case A, which emphasizes the importance of human-centered AI and the need for interacting organizational practices. (ML: 0.95)
- Interacting organizational practices: The essential types of practices that need to accompany human-centered AI, including continuous learning and improvement, feedback mechanisms, regular meetings and updates, clear roles and responsibilities, effective communication, collaboration between experts, adaptation processes, documentation and knowledge management, monitoring and evaluation, and continuous refinement of the AI system. (ML: 0.94)
- Feedback mechanisms, 3. (ML: 0.93)
- Continuous refinement of the AI system. (ML: 0.91)
- Documentation and knowledge management, 9. (ML: 0.89)
- Regular meetings and updates, 4. (ML: 0.89)
Abstract
This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical perspective to comply with the requirements of Human-centered AI (HCAI). Instead of viewing AI merely as a technical tool, the analysis emphasizes the importance of embedding AI into communication, collaboration, and decision-making processes within organizations from a human-centered perspective. Ten case-based patterns illustrate how AI support of predictive maintenance can be organized to address quality assurance and continuous improvement and to provide different types of sup-port for HCAI. The analysis shows that AI adoption often requires and enables new forms of organizational learning, where specialists jointly interpret AI output, adapt workflows, and refine rules for system improve-ment. Different dimensions and levels of socio-technical integration of AI are considered to reflect the effort and benefits of keeping the organization in the loop.
This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical perspective to comply with the requirements of Human-centered AI (HCAI). Instead of viewing AI merely as a technical tool, the analysis emphasizes the importance of embedding AI into communication, collaboration, and decision-making processes within organizations from a human-centered perspective. Ten case-based patterns illustrate how AI support of predictive maintenance can be organized to address quality assurance and continuous improvement and to provide different types of sup-port for HCAI. The analysis shows that AI adoption often requires and enables new forms of organizational learning, where specialists jointly interpret AI output, adapt workflows, and refine rules for system improve-ment. Different dimensions and levels of socio-technical integration of AI are considered to reflect the effort and benefits of keeping the organization in the loop.
Why we are recommending this paper?
Because ai and society is a popular topic and you have less than 3 interests with available recommendations
Because ai and society is a popular topic and you have less than 3 interests with available recommendations
NYU Grossman School of Medicine
AI Insights
- The dataset includes images of skin lesions, which are annotated with labels indicating the type of lesion and its severity. (ML: 0.94)
- The dataset can be used for training machine learning models to diagnose skin conditions from images. (ML: 0.91)
- Digital pathology: The practice of using digital tools and techniques to analyze and interpret histopathological images. (ML: 0.91)
- The dataset is available for download and use by researchers and clinicians. (ML: 0.91)
- The preprocessed dataset ensures that patient privacy is maintained while still allowing for meaningful analysis and annotation. (ML: 0.90)
- The dataset is a valuable resource for researchers and clinicians working in the field of dermatopathology. (ML: 0.90)
- The dataset has been preprocessed to remove identifying information and ensure patient privacy. (ML: 0.89)
- The dataset is a collection of images from various sources, including publicly available datasets and private collections. (ML: 0.86)
- De-identification: The process of removing identifying information from medical images to ensure patient privacy. (ML: 0.84)
- Whole-slide imaging (WSI): A technique that captures high-resolution images of entire slides, allowing for detailed analysis and annotation. (ML: 0.80)
Abstract
Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and dermatopathology trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6\% for the deep learning approach, 61.0\% for the keyword-based retrieval method, and 90.4\% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.
Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and dermatopathology trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6\% for the deep learning approach, 61.0\% for the keyword-based retrieval method, and 90.4\% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.
Why we are recommending this paper?
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
Radboud University
AI Insights
- Value-Sensitive Design (VSD) can help the community reflect on how genAI tools affect learning, expertise development, and knowledge passing, and make choices about tools, incentives, and evaluation practices with explicit attention to agency, responsibility, and learning. (ML: 0.99)
- The community should support practices that preserve technical grounding, encourage verification, and maintain human responsibility, rather than relying solely on efficiency and automation. (ML: 0.98)
- Researchers are losing technical grounding and becoming dependent on automated systems, which can lead to errors and accountability issues. (ML: 0.98)
- A renewed emphasis on first-principles thinking, verification literacy, and resilience in research practice is necessary to ensure that researchers remain responsible for their outputs and capable of intervening when AI tools fail. (ML: 0.98)
- The software engineering research community must prioritize human responsibility and accountability in the face of widespread AI assistance. (ML: 0.98)
- Resilience in Research Practice: The capacity to reason about and solve problems without continuous reliance on automated systems. (ML: 0.97)
- Value-Sensitive Design (VSD): A research and design approach that explicitly accounts for human values throughout the design, development, and use of technology. (ML: 0.97)
- Verification Literacy: The ability to audit and test AI-generated outputs in a rigorous way, requiring deeper technical understanding. (ML: 0.97)
- The software engineering research community is at a crossroads as AI-based tools become more prevalent in their work. (ML: 0.96)
- Design Fiction: A narrative technique used to explore the implications of emerging technologies on society. (ML: 0.92)
Abstract
Rising publication pressure and the routine use of generative AI tools are reshaping how software engineering research is produced, assessed, and taught. While these developments promise efficiency, they also raise concerns about skill degradation, responsibility, and trust in scholarly outputs. This vision paper employs Design Fiction as a methodological lens to examine how such concerns might materialise if current practices persist. Drawing on themes reported in a recent community survey, we construct a speculative artifact situated in a near future research setting. The fiction is used as an analytical device rather than a forecast, enabling reflection on how automated assistance might impede domain knowledge competence, verification, and mentoring practices. By presenting an intentionally unsettling scenario, the paper invites discussion on how the software engineering research community in the future will define proficiency, allocate responsibility, and support learning.
Rising publication pressure and the routine use of generative AI tools are reshaping how software engineering research is produced, assessed, and taught. While these developments promise efficiency, they also raise concerns about skill degradation, responsibility, and trust in scholarly outputs. This vision paper employs Design Fiction as a methodological lens to examine how such concerns might materialise if current practices persist. Drawing on themes reported in a recent community survey, we construct a speculative artifact situated in a near future research setting. The fiction is used as an analytical device rather than a forecast, enabling reflection on how automated assistance might impede domain knowledge competence, verification, and mentoring practices. By presenting an intentionally unsettling scenario, the paper invites discussion on how the software engineering research community in the future will define proficiency, allocate responsibility, and support learning.
Why we are recommending this paper?
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
Syracuse University
AI Insights
- The framework's performance may be affected by the quality of input data and the complexity of the query. (ML: 0.95)
- The benchmark evaluation only considers a limited set of intelligence modes, which may not fully represent the range of possible designs. (ML: 0.93)
- Agentic AI: An artificial intelligence that can act on behalf of humans to achieve specific goals. (ML: 0.91)
- Previous studies have shown that agentic AI can improve building energy management through optimized control policies and coordinated control strategies. (ML: 0.85)
- The benchmark evaluation highlights the importance of intelligence mode design in achieving balanced performance, with centralized two-stage mode providing the most reliable results while maintaining low execution latency and inference cost. (ML: 0.85)
- The results show the impact of system upgrades on thermal and electrical domain performance. (ML: 0.83)
- The proposed agentic AI framework demonstrates its ability to execute complex building energy management queries through sequential simulations. (ML: 0.81)
- The proposed agentic AI framework executes a realistic building energy management query through three sequential simulations: baseline configuration, system upgrade, and system upgrade with control upgrade. (ML: 0.78)
- MCP (Model-Component Platform): A platform for integrating models and components. (ML: 0.76)
- DER (Distributed Energy Resources): Devices or systems that generate, store, or manage energy locally. (ML: 0.75)
- PIML (Physical Information Modeling Language): A tool for modeling and simulating physical systems. (ML: 0.61)
Abstract
The urgent need for building decarbonization calls for a paradigm shift in future autonomous building energy operation, from human-intensive engineering workflows toward intelligent agents that interact with physics-grounded digital environments. This study proposes an end-to-end agentic AI-enabled Physics-Informed Machine Learning (PIML) environment for scalable building energy modeling, simulation, control, and automation. The framework consists of (1) a modular and physics-consistent PIML digital environment spanning building thermal dynamics, Heating, Ventilation, and Air Conditioning (HVAC), and distributed energy resources (DER) for grid-interactive energy management; and (2) an agentic AI layer with 11 specialist agents and 72 Model Context Protocol (MCP) tools that enable end-to-end execution of multi-step energy analytics. A representative case study demonstrates multi-domain, multi-agent coordination for assessing how system and control upgrades affect energy use, operating cost, thermal comfort, and flexibility. In addition, a large-scale benchmark (about 4000 runs) systematically evaluates workflow performance in terms of accuracy, token consumption, execution time, and inference cost. The results quantify the impacts of intelligence mode design, model size, task complexity, and orchestrator-specialist coordination, and provide key lessons for building future agentic AI systems in real-world building energy applications. This work establishes a scalable, physics-grounded foundation for deploying agentic AI in decarbonized and grid-interactive building operations.
The urgent need for building decarbonization calls for a paradigm shift in future autonomous building energy operation, from human-intensive engineering workflows toward intelligent agents that interact with physics-grounded digital environments. This study proposes an end-to-end agentic AI-enabled Physics-Informed Machine Learning (PIML) environment for scalable building energy modeling, simulation, control, and automation. The framework consists of (1) a modular and physics-consistent PIML digital environment spanning building thermal dynamics, Heating, Ventilation, and Air Conditioning (HVAC), and distributed energy resources (DER) for grid-interactive energy management; and (2) an agentic AI layer with 11 specialist agents and 72 Model Context Protocol (MCP) tools that enable end-to-end execution of multi-step energy analytics. A representative case study demonstrates multi-domain, multi-agent coordination for assessing how system and control upgrades affect energy use, operating cost, thermal comfort, and flexibility. In addition, a large-scale benchmark (about 4000 runs) systematically evaluates workflow performance in terms of accuracy, token consumption, execution time, and inference cost. The results quantify the impacts of intelligence mode design, model size, task complexity, and orchestrator-specialist coordination, and provide key lessons for building future agentic AI systems in real-world building energy applications. This work establishes a scalable, physics-grounded foundation for deploying agentic AI in decarbonized and grid-interactive building operations.
Why we are recommending this paper?
Because agi: artificial general intelligence is a popular topic and you have less than 3 interests with available recommendations
Because agi: artificial general intelligence is a popular topic and you have less than 3 interests with available recommendations
Universit Paris Cit , CNRS
AI Insights
- The authors show that any feedforward network with ReLU activations can be viewed as a place-independent IFS, and they extend this result to other types of neural networks, including residual blocks and MoE models. (ML: 0.92)
- The paper discusses the interpretation of deep neural networks as iterated function systems (IFSs) and provides a general framework for analyzing their convergence properties. (ML: 0.89)
- The paper provides several examples of neural network architectures that can be interpreted as IFSs, including ResNet with Softplus activation, Transformer block, and MoE model. (ML: 0.88)
- The authors use the Hutchinson operator to analyze the convergence properties of IFSs and show that they can be used to bound the Wasserstein distance between the output of a neural network and its fixed point. (ML: 0.87)
- Definition 1: A Markov recursion is a sequence of random variables {Xn} defined by X0 = x and Xt+1 = w(Xt, Ξ), where w is a function that depends on the current state Xt and the parameter Ξ. (ML: 0.82)
- Definition 3: A place-dependent IFS (P-IFS) is an IFS {wΞΎ} where each wΞΎ depends on the current state x and the parameter Ξ. (ML: 0.80)
- Definition 2: An iterated function system (IFS) is a collection of functions {wΞΎ} indexed by ΞΎ β I, where each wΞΎ is a Lipschitz map from X to itself. (ML: 0.80)
- They also introduce the concept of strong average Lipschitz contractivity for place-dependent IFSs and provide conditions under which it holds. (ML: 0.75)
- Definition 5: A P-IFS {wΞΎ} is strongly average-contractive if sup_xβX β_{ΞΎβI} pΞΎ(x)cΞΎ β€ c < 1. (ML: 0.67)
- Definition 4: The Hutchinson operator T is a contraction on the space of probability measures PP(X) with respect to the Wasserstein distance W2 if there exists a constant c < 1 such that W2(T(Β΅), T(Ξ½)) β€ cW2(Β΅, Ξ½) for all Β΅, Ξ½ β PP(X). (ML: 0.67)
- The Hutchinson operator T is defined as T(Β΅) = β_{ΞΎβI} pwΞΎ#Β΅q. (ML: 0.49)
Abstract
Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of parametrized functions, a mechanism that can be unstable and difficult to train, making stability a primary concern. Even when training succeeds, there are few rigorous results on how well such models generalize beyond the observed data, especially in the generative setting. In this work, we leverage the theory of stochastic Iterated Function Systems (IFS) and show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS. This connection allows us to import results from random dynamical systems to (i) establish the existence and uniqueness of invariant measures under suitable contractivity assumptions, and (ii) derive a Wasserstein generalization bound for generative modeling. The bound naturally leads to a new training objective that directly controls the collage-type approximation error between the data distribution and its image under the learned transfer operator. We illustrate the theory on a controlled 2D example and empirically evaluate the proposed objective on standard image datasets (MNIST, CelebA, CIFAR-10).
Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of parametrized functions, a mechanism that can be unstable and difficult to train, making stability a primary concern. Even when training succeeds, there are few rigorous results on how well such models generalize beyond the observed data, especially in the generative setting. In this work, we leverage the theory of stochastic Iterated Function Systems (IFS) and show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS. This connection allows us to import results from random dynamical systems to (i) establish the existence and uniqueness of invariant measures under suitable contractivity assumptions, and (ii) derive a Wasserstein generalization bound for generative modeling. The bound naturally leads to a new training objective that directly controls the collage-type approximation error between the data distribution and its image under the learned transfer operator. We illustrate the theory on a controlled 2D example and empirically evaluate the proposed objective on standard image datasets (MNIST, CelebA, CIFAR-10).
Why we are recommending this paper?
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Harvard University
AI Insights
- Milestones serve dual pedagogical and validation purposes, providing motivation through historical framing and demonstrating implementation correctness through real-world task performance. (ML: 0.98)
- Each module concludes with systems reasoning prompts measuring conceptual understanding beyond syntactic correctness. (ML: 0.97)
- Milestones are designed to be challenging but achievable, allowing students to demonstrate their understanding of complex concepts through real-world tasks. (ML: 0.96)
- Assessment validates both isolated correctness and cross-module integration. (ML: 0.96)
- The TinyTorch framework is designed for teaching machine learning concepts through hands-on implementation and analysis. (ML: 0.95)
- Reflect: Systems Analysis Questions. (ML: 0.94)
- TinyTorch follows a consistent Build-Use-Reflect cycle, integrating implementation, application, and systems reasoning to address multiple learning objectives. (ML: 0.94)
- It's a pedagogical tool aimed at bridging the gap between theoretical understanding and practical application. (ML: 0.94)
- Students implement components in Jupyter notebooks with scaffolded guidance. (ML: 0.91)
- TinyTorch's design emphasizes systems thinking, encouraging students to analyze and understand the relationships between components, rather than just focusing on individual functions. (ML: 0.87)
- The framework includes six historical milestones that recreate actual breakthroughs using exclusively student code, validating success through task-appropriate performance. (ML: 0.85)
- The framework is built with a focus on explicit dependencies, making it easier for students to understand where each module fits in the larger architecture. (ML: 0.83)
- Use: Integration Testing Beyond Unit Tests. (ML: 0.77)
- Build: Implementation with Explicit Dependencies. (ML: 0.66)
Abstract
Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling, optimizer theory without knowing why Adam requires 3x the memory of SGD. This "algorithm-systems divide" produces practitioners who can train models but cannot debug memory failures, optimize inference latency, or reason about deployment trade-offs--the very skills industry demands as "ML systems engineering." We present TinyTorch, a 20-module curriculum that closes this gap through "implementation-based systems pedagogy": students construct PyTorch's core components (tensors, autograd, optimizers, CNNs, transformers) in pure Python, building a complete framework where every operation they invoke is code they wrote. The design employs three patterns: "progressive disclosure" of complexity, "systems-first integration" of profiling from the first module, and "build-to-validate milestones" recreating 67 years of ML breakthroughs--from Perceptron (1958) through Transformers (2017) to MLPerf-style benchmarking. Requiring only 4GB RAM and no GPU, TinyTorch demonstrates that deep ML systems understanding is achievable without specialized hardware. The curriculum is available open-source at mlsysbook.ai/tinytorch.
Machine learning education faces a fundamental gap: students learn algorithms without understanding the systems that execute them. They study gradient descent without measuring memory, attention mechanisms without analyzing O(N^2) scaling, optimizer theory without knowing why Adam requires 3x the memory of SGD. This "algorithm-systems divide" produces practitioners who can train models but cannot debug memory failures, optimize inference latency, or reason about deployment trade-offs--the very skills industry demands as "ML systems engineering." We present TinyTorch, a 20-module curriculum that closes this gap through "implementation-based systems pedagogy": students construct PyTorch's core components (tensors, autograd, optimizers, CNNs, transformers) in pure Python, building a complete framework where every operation they invoke is code they wrote. The design employs three patterns: "progressive disclosure" of complexity, "systems-first integration" of profiling from the first module, and "build-to-validate milestones" recreating 67 years of ML breakthroughs--from Perceptron (1958) through Transformers (2017) to MLPerf-style benchmarking. Requiring only 4GB RAM and no GPU, TinyTorch demonstrates that deep ML systems understanding is achievable without specialized hardware. The curriculum is available open-source at mlsysbook.ai/tinytorch.
Why we are recommending this paper?
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
Southeast University
AI Insights
- Artifact-aware evaluation framework: A comprehensive framework for evaluating video generation models based on their ability to detect and correct artifacts. (ML: 0.94)
- The proposed framework provides a comprehensive evaluation of video generation models, enabling researchers to identify areas for improvement. (ML: 0.94)
- Video quality assessment methods: Techniques for evaluating the quality of generated videos based on various metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). (ML: 0.93)
- The novel DV AR (Dense Video Artifact Recognition) framework is proposed, which leverages the strengths of both text-to-video diffusion models and video quality assessment methods. (ML: 0.91)
- The paper proposes a comprehensive artifact-aware evaluation framework for video generation, focusing on fine-grained artifact detection across Appearance, Motion, and Camera dimensions. (ML: 0.91)
- Experimental results demonstrate the accuracy of the approach in identifying artifacts in generated videos, with a significant improvement over state-of-the-art methods. (ML: 0.90)
- Text-to-video diffusion models: A type of deep learning model that generates videos from text descriptions. (ML: 0.88)
- Fine-grained artifact detection: The process of detecting specific types of artifacts in videos, such as noise, blurriness, or color distortion. (ML: 0.87)
- The large-scale GenVID dataset is introduced, which includes a wide range of videos with diverse content, styles, and quality levels. (ML: 0.87)
- The FMG-DFS strategy enhances temporal localization, enabling more precise and efficient artifact detection. (ML: 0.68)
Abstract
With the rapid advancement of video generation techniques, evaluating and auditing generated videos has become increasingly crucial. Existing approaches typically offer coarse video quality scores, lacking detailed localization and categorization of specific artifacts. In this work, we introduce a comprehensive evaluation protocol focusing on three key aspects affecting human perception: Appearance, Motion, and Camera. We define these axes through a taxonomy of 10 prevalent artifact categories reflecting common generative failures observed in video generation. To enable robust artifact detection and categorization, we introduce GenVID, a large-scale dataset of 80k videos generated by various state-of-the-art video generation models, each carefully annotated for the defined artifact categories. Leveraging GenVID, we develop DVAR, a Dense Video Artifact Recognition framework for fine-grained identification and classification of generative artifacts. Extensive experiments show that our approach significantly improves artifact detection accuracy and enables effective filtering of low-quality content.
With the rapid advancement of video generation techniques, evaluating and auditing generated videos has become increasingly crucial. Existing approaches typically offer coarse video quality scores, lacking detailed localization and categorization of specific artifacts. In this work, we introduce a comprehensive evaluation protocol focusing on three key aspects affecting human perception: Appearance, Motion, and Camera. We define these axes through a taxonomy of 10 prevalent artifact categories reflecting common generative failures observed in video generation. To enable robust artifact detection and categorization, we introduce GenVID, a large-scale dataset of 80k videos generated by various state-of-the-art video generation models, each carefully annotated for the defined artifact categories. Leveraging GenVID, we develop DVAR, a Dense Video Artifact Recognition framework for fine-grained identification and classification of generative artifacts. Extensive experiments show that our approach significantly improves artifact detection accuracy and enables effective filtering of low-quality content.
Why we are recommending this paper?
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Rutgers University
AI Insights
- Generative models: A class of machine learning algorithms that can generate new data samples based on a given dataset. (ML: 0.97)
- The paper assumes that the input text is well-formed and does not contain any errors or ambiguities. (ML: 0.97)
- Diffusion prior constraints: A type of regularization technique used in generative models that encourages the model to produce samples that are similar to the data distribution. (ML: 0.92)
- The paper discusses the concept of ConceptLab, a creative generation system that uses diffusion prior constraints to generate novel images. (ML: 0.90)
- ConceptLab is based on a combination of generative models and text-image harmony, which allows it to produce high-quality images with specific styles and concepts. (ML: 0.88)
- ConceptLab is based on a combination of generative models and text-image harmony, which allows it to produce high-quality images with specific styles and concepts. (ML: 0.88)
- The paper presents ConceptLab, a creative generation system that uses diffusion prior constraints to generate novel images. (ML: 0.86)
- The authors propose a new method for training generative models using diffusion prior constraints, which enables the model to learn from the data distribution and generate novel samples. (ML: 0.84)
- The authors propose a new method for training generative models using diffusion prior constraints, which enables the model to learn from the data distribution and generate novel samples. (ML: 0.84)
- Text-image harmony: A method for combining text and image features to generate images with specific styles and concepts. (ML: 0.76)
Abstract
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative generation using diffusion models, where creativity is associated with the inverse probability of an image's existence in the CLIP embedding space. Unlike prior approaches that rely on a manual blending of concepts or exclusion of subcategories, our method calculates the probability distribution of generated images and drives it towards low-probability regions to produce rare, imaginative, and visually captivating outputs. We also introduce pullback mechanisms, achieving high creativity without sacrificing visual fidelity. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness and efficiency of our creative generation framework, showcasing its ability to produce unique, novel, and thought-provoking images. This work provides a new perspective on creativity in generative models, offering a principled method to foster innovation in visual content synthesis.
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative generation using diffusion models, where creativity is associated with the inverse probability of an image's existence in the CLIP embedding space. Unlike prior approaches that rely on a manual blending of concepts or exclusion of subcategories, our method calculates the probability distribution of generated images and drives it towards low-probability regions to produce rare, imaginative, and visually captivating outputs. We also introduce pullback mechanisms, achieving high creativity without sacrificing visual fidelity. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness and efficiency of our creative generation framework, showcasing its ability to produce unique, novel, and thought-provoking images. This work provides a new perspective on creativity in generative models, offering a principled method to foster innovation in visual content synthesis.
Why we are recommending this paper?
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Because image and video generation is a popular topic and you have less than 3 interests with available recommendations
Interests not found
We did not find any papers that match the below interests.
Try other terms also consider if the content exists in arxiv.org.
- SQL
- Database Design
You can edit or add more interests any time.
π¬ Help Shape Our Pricing
We're exploring pricing options to make this project sustainable. Take 3 minutes to share what you'd be willing to pay (if anything). Your input guides our future investment.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback