University of Texas at Dallas
Abstract
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.
Why we are recommending this paper?
Due to your Interest in AI Agents
This paper directly addresses the need for memory augmentation in LLM-based agents, a key area for building more robust and capable AI agents. The multi-graph approach offers a promising solution to the limitations of existing memory systems, aligning with the user’s interest in LLMs for AI agents.
Due to your Interest in AI Agents
This paper directly addresses the need for memory augmentation in LLM-based agents, a key area for building more robust and capable AI agents. The multi-graph approach offers a promising solution to the limitations of existing memory systems, aligning with the user’s interest in LLMs for AI agents.
Kaze Technologies
Abstract
This paper formalises the literature on emerging design patterns and paradigms for Large Language Model (LLM)-enabled multi-agent systems (MAS), evaluating their practical utility across various domains. We define key architectural components, including agent orchestration, communication mechanisms, and control-flow strategies, and demonstrate how these enable rapid development of modular, domain-adaptive solutions. Three real-world case studies are tested in controlled, containerised pilots in telecommunications security, national heritage asset management, and utilities customer service automation. Initial empirical results show that, for these case studies, prototypes were delivered within two weeks and pilot-ready solutions within one month, suggesting reduced development overhead compared to conventional approaches and improved user accessibility. However, findings also reinforce limitations documented in the literature, including variability in LLM behaviour that leads to challenges in transitioning from prototype to production maturity. We conclude by outlining critical research directions for improving reliability, scalability, and governance in MAS architectures and the further work needed to mature MAS design patterns to mitigate the inherent challenges.
This paper formalises the literature on emerging design patterns and paradigms for Large Language Model (LLM)-enabled multi-agent systems (MAS), evaluating their practical utility across various domains. We define key architectural components, including agent orchestration, communication mechanisms, and control-flow strategies, and demonstrate how these enable rapid development of modular, domain-adaptive solutions. Three real-world case studies are tested in controlled, containerised pilots in telecommunications security, national heritage asset management, and utilities customer service automation. Initial empirical results show that, for these case studies, prototypes were delivered within two weeks and pilot-ready solutions within one month, suggesting reduced development overhead compared to conventional approaches and improved user accessibility. However, findings also reinforce limitations documented in the literature, including variability in LLM behaviour that leads to challenges in transitioning from prototype to production maturity. We conclude by outlining critical research directions for improving reliability, scalability, and governance in MAS architectures and the further work needed to mature MAS design patterns to mitigate the inherent challenges.
Why we are recommending this paper?
Due to your Interest in LLMs for AI Agents
Given the user's focus on AI agents, this paper’s formalization of LLM-enabled multi-agent system design patterns is highly relevant. It provides a structured approach to understanding and building complex agentic systems, a critical area of interest.
Due to your Interest in LLMs for AI Agents
Given the user's focus on AI agents, this paper’s formalization of LLM-enabled multi-agent system design patterns is highly relevant. It provides a structured approach to understanding and building complex agentic systems, a critical area of interest.
Honda Research Institute Europe GmbH
Abstract
Large language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. This paper presents a case study of using ChatGPT for rapid prototyping in ESA's ELOPE (Event-based Lunar OPtical flow Egomotion estimation) competition. The competition required participants to process event camera data to estimate lunar lander trajectories. Despite joining late, we achieved second place with a score of 0.01282, highlighting the potential of human-AI collaboration in competitive scientific settings. ChatGPT contributed not only executable code but also algorithmic reasoning, data handling routines, and methodological suggestions, such as using fixed number of events instead of fixed time spans for windowing. At the same time, we observed limitations: the model often introduced unnecessary structural changes, gets confused by intermediate discussions about alternative ideas, occasionally produced critical errors and forgets important aspects in longer scientific discussions. By analyzing these strengths and shortcomings, we show how conversational AI can both accelerate development and support conceptual insight in scientific research. We argue that structured integration of LLMs into the scientific workflow can enhance rapid prototyping by proposing best practices for AI-assisted scientific work.
Large language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. This paper presents a case study of using ChatGPT for rapid prototyping in ESA's ELOPE (Event-based Lunar OPtical flow Egomotion estimation) competition. The competition required participants to process event camera data to estimate lunar lander trajectories. Despite joining late, we achieved second place with a score of 0.01282, highlighting the potential of human-AI collaboration in competitive scientific settings. ChatGPT contributed not only executable code but also algorithmic reasoning, data handling routines, and methodological suggestions, such as using fixed number of events instead of fixed time spans for windowing. At the same time, we observed limitations: the model often introduced unnecessary structural changes, gets confused by intermediate discussions about alternative ideas, occasionally produced critical errors and forgets important aspects in longer scientific discussions. By analyzing these strengths and shortcomings, we show how conversational AI can both accelerate development and support conceptual insight in scientific research. We argue that structured integration of LLMs into the scientific workflow can enhance rapid prototyping by proposing best practices for AI-assisted scientific work.
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 case study, originating from Honda Research Institute Europe GmbH, demonstrates the practical application of LLMs in accelerating scientific prototyping – a direct match to the user's interest in AI agents for innovation. The focus on a specific competition (ELOPE) provides a tangible example of this technology’s potential.
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
This case study, originating from Honda Research Institute Europe GmbH, demonstrates the practical application of LLMs in accelerating scientific prototyping – a direct match to the user's interest in AI agents for innovation. The focus on a specific competition (ELOPE) provides a tangible example of this technology’s potential.
University of Ottawa
AI Insights
- Retrieval is binary and essential, with systems achieving either 0% or 100% retrieval success—no intermediate performance exists. [3]
- Retrieval-Augmented Generation (RAG): A technique that combines retrieval of relevant information from a database with generation of text based on the retrieved information. [3]
- Causal Graphs: Visual representations of causal relationships between variables, used to model and analyze complex systems. [3]
- This research demonstrates the effectiveness of causal graph-enhanced RAG in achieving high accuracy and eliminating hallucinations in medical evidence synthesis. [3]
- The study highlights the importance of retrieval mechanisms in AI-assisted healthcare, emphasizing the need for systems to access relevant information from databases to generate accurate responses. [3]
- The study's reliance on a specific dataset and evaluation metrics may limit its generalizability to other domains or applications. [3]
- Causal graph-enhanced retrieval-augmented generation (RAG) achieves 95% accuracy with zero hallucinations through explicit causal reasoning integrated with retrieval mechanisms. [2]
Abstract
Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.
Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.
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
The paper’s exploration of causal AI agents for systematic review addresses a significant challenge in medical research, aligning with the user’s interest in AI agents. The focus on reducing hallucinations in AI models is particularly relevant for building reliable agentic systems.
Because research automation with ai is a popular topic and you have less than 3 interests with available recommendations
The paper’s exploration of causal AI agents for systematic review addresses a significant challenge in medical research, aligning with the user’s interest in AI agents. The focus on reducing hallucinations in AI models is particularly relevant for building reliable agentic systems.
University of Essex
Abstract
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach, termed Stochastic Latent Differential Inference (SLDI), embeds an Itô SDE in the latent space of a variational autoencoder, allowing for flexible, continuous-time modeling of uncertainty while preserving a principled mathematical foundation. The drift and diffusion terms of the SDE are parameterized by neural networks, enabling data-driven inference and generalizing classical time series models to handle irregular sampling and complex dynamic structure. A central theoretical contribution is the co-parameterization of the adjoint state with a dedicated neural network, forming a coupled forward-backward system that captures not only latent evolution but also gradient dynamics. I introduce a pathwise-regularized adjoint loss and analyze variance-reduced gradient flows through the lens of stochastic calculus, offering new tools for improving training stability in deep latent SDEs. My paper unifies and extends variational inference, continuous-time generative modeling, and control-theoretic optimization, providing a rigorous foundation for future developments in stochastic probabilistic machine learning.
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach, termed Stochastic Latent Differential Inference (SLDI), embeds an Itô SDE in the latent space of a variational autoencoder, allowing for flexible, continuous-time modeling of uncertainty while preserving a principled mathematical foundation. The drift and diffusion terms of the SDE are parameterized by neural networks, enabling data-driven inference and generalizing classical time series models to handle irregular sampling and complex dynamic structure. A central theoretical contribution is the co-parameterization of the adjoint state with a dedicated neural network, forming a coupled forward-backward system that captures not only latent evolution but also gradient dynamics. I introduce a pathwise-regularized adjoint loss and analyze variance-reduced gradient flows through the lens of stochastic calculus, offering new tools for improving training stability in deep latent SDEs. My paper unifies and extends variational inference, continuous-time generative modeling, and control-theoretic optimization, providing a rigorous foundation for future developments in stochastic probabilistic machine learning.
Why we are recommending this paper?
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
This work proposes a novel framework for uncertainty quantification, a crucial aspect of building robust and reliable AI agents. The integration of SDEs with deep generative models offers a sophisticated approach to handling uncertainty in temporal data, aligning with the user's interest in agentic AI.
Because deep learning is a popular topic and you have less than 3 interests with available recommendations
This work proposes a novel framework for uncertainty quantification, a crucial aspect of building robust and reliable AI agents. The integration of SDEs with deep generative models offers a sophisticated approach to handling uncertainty in temporal data, aligning with the user's interest in agentic AI.
Prince Sultan University
AI Insights
- The paper discusses the concept of agentic AI, which refers to AI systems that can make decisions and take actions on their own without human intervention. [3]
- Autonomous agent: An AI system that can operate independently and make decisions based on its internal state and external environment. [3]
- Agentic AI is a rapidly growing field with various applications, including scientific discovery, language translation, and task management. [2]
Abstract
The evolution of Large Language Models (LLMs) from passive text generators to autonomous, goal-driven systems represents a fundamental shift in artificial intelligence. This chapter examines the emergence of agentic AI systems that integrate planning, memory, tool use, and iterative reasoning to operate autonomously in complex environments. We trace the architectural progression from statistical models to transformer-based systems, identifying capabilities that enable agentic behavior: long-range reasoning, contextual awareness, and adaptive decision-making. The chapter provides three contributions: (1) a synthesis of how LLM capabilities extend toward agency through reasoning-action-reflection loops; (2) an integrative framework describing core components perception, memory, planning, and tool execution that bridge LLMs with autonomous behavior; (3) a critical assessment of applications and persistent challenges in safety, alignment, reliability, and sustainability. Unlike existing surveys, we focus on the architectural transition from language understanding to autonomous action, emphasizing the technical gaps that must be resolved before deployment. We identify critical research priorities, including verifiable planning, scalable multi-agent coordination, persistent memory architectures, and governance frameworks. Responsible advancement requires simultaneous progress in technical robustness, interpretability, and ethical safeguards to realize potential while mitigating risks of misalignment and unintended consequences.
The evolution of Large Language Models (LLMs) from passive text generators to autonomous, goal-driven systems represents a fundamental shift in artificial intelligence. This chapter examines the emergence of agentic AI systems that integrate planning, memory, tool use, and iterative reasoning to operate autonomously in complex environments. We trace the architectural progression from statistical models to transformer-based systems, identifying capabilities that enable agentic behavior: long-range reasoning, contextual awareness, and adaptive decision-making. The chapter provides three contributions: (1) a synthesis of how LLM capabilities extend toward agency through reasoning-action-reflection loops; (2) an integrative framework describing core components perception, memory, planning, and tool execution that bridge LLMs with autonomous behavior; (3) a critical assessment of applications and persistent challenges in safety, alignment, reliability, and sustainability. Unlike existing surveys, we focus on the architectural transition from language understanding to autonomous action, emphasizing the technical gaps that must be resolved before deployment. We identify critical research priorities, including verifiable planning, scalable multi-agent coordination, persistent memory architectures, and governance frameworks. Responsible advancement requires simultaneous progress in technical robustness, interpretability, and ethical safeguards to realize potential while mitigating risks of misalignment and unintended consequences.
Why we are recommending this paper?
Due to your Interest in AI Agents
Due to your Interest in AI Agents
Luxembourg Institute of Science and Technology
Abstract
LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.
LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.
Why we are recommending this paper?
Due to your Interest in LLMs for AI Agents
Due to your Interest in LLMs for AI Agents
University of Zurich
AI Insights
- The study examines the effects of emotional prompts on ChatGPT's performance in addressing ethical dilemmas and its impact on human communication. [3]
- The study also found that emotional prompts can influence human communication, with participants in the emotional conditions exhibiting more negative emotions and hostile language. [3]
- Additionally, the study only examines a limited range of emotional conditions, which may not capture the full scope of emotional influences on ChatGPT's performance. [3]
- Previous studies have shown that large language models like ChatGPT can be influenced by emotional stimuli and can exhibit biases in their responses. [3]
- The current study builds on this research by examining the specific effects of emotional prompts on ChatGPT's performance and its impact on human communication. [3]
- The study investigates how emotional prompts affect ChatGPT's performance and its impact on human communication. [3]
- The study explores how emotional prompts affect a language model called ChatGPT, which is designed to provide helpful answers to questions. [3]
- The researchers found that when people use emotional words like 'blame' or 'praise', it can make ChatGPT give better answers and also change the way people communicate with each other. [3]
- ChatGPT: A large language model developed by OpenAI that can generate human-like text based on input prompts. [2]
Abstract
This research examines how the emotional tone of human-AI interactions shapes ChatGPT and human behavior. In a between-subject experiment, we asked participants to express a specific emotion while working with ChatGPT (GPT-4.0) on two tasks, including writing a public response and addressing an ethical dilemma. We found that compared to interactions where participants maintained a neutral tone, ChatGPT showed greater improvement in its answers when participants praised ChatGPT for its responses. Expressing anger towards ChatGPT also led to a higher albeit smaller improvement relative to the neutral condition, whereas blaming ChatGPT did not improve its answers. When addressing an ethical dilemma, ChatGPT prioritized corporate interests less when participants expressed anger towards it, while blaming increases its emphasis on protecting the public interest. Additionally, we found that people used more negative, hostile, and disappointing expressions in human-human communication after interactions during which participants blamed rather than praised for their responses. Together, our findings demonstrate that the emotional tone people apply in human-AI interactions not only shape ChatGPT's outputs but also carry over into subsequent human-human communication.
This research examines how the emotional tone of human-AI interactions shapes ChatGPT and human behavior. In a between-subject experiment, we asked participants to express a specific emotion while working with ChatGPT (GPT-4.0) on two tasks, including writing a public response and addressing an ethical dilemma. We found that compared to interactions where participants maintained a neutral tone, ChatGPT showed greater improvement in its answers when participants praised ChatGPT for its responses. Expressing anger towards ChatGPT also led to a higher albeit smaller improvement relative to the neutral condition, whereas blaming ChatGPT did not improve its answers. When addressing an ethical dilemma, ChatGPT prioritized corporate interests less when participants expressed anger towards it, while blaming increases its emphasis on protecting the public interest. Additionally, we found that people used more negative, hostile, and disappointing expressions in human-human communication after interactions during which participants blamed rather than praised for their responses. Together, our findings demonstrate that the emotional tone people apply in human-AI interactions not only shape ChatGPT's outputs but also carry over into subsequent human-human communication.
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
Institute for Applied Economic Research IPEA Brazil
Abstract
This paper examines the European Union's emerging regulatory landscape - focusing on the AI Act, corporate sustainability reporting and due diligence regimes (CSRD and CSDDD), and data center regulation - to assess whether it can effectively govern AI's environmental footprint. We argue that, despite incremental progress, current approaches remain ill-suited to correcting the market failures underpinning AI-related energy use, water consumption, and material demand. Key shortcomings include narrow disclosure requirements, excessive reliance on voluntary standards, weak enforcement mechanisms, and a structural disconnect between AI-specific impacts and broader sustainability laws. The analysis situates these regulatory gaps within a wider ecosystem of academic research, civil society advocacy, standard-setting, and industry initiatives, highlighting risks of regulatory capture and greenwashing. Building on this diagnosis, the paper advances strategic recommendations for the COP30 Action Agenda, calling for binding transparency obligations, harmonized international standards for lifecycle assessment, stricter governance of data center expansion, and meaningful public participation in AI infrastructure decisions.
This paper examines the European Union's emerging regulatory landscape - focusing on the AI Act, corporate sustainability reporting and due diligence regimes (CSRD and CSDDD), and data center regulation - to assess whether it can effectively govern AI's environmental footprint. We argue that, despite incremental progress, current approaches remain ill-suited to correcting the market failures underpinning AI-related energy use, water consumption, and material demand. Key shortcomings include narrow disclosure requirements, excessive reliance on voluntary standards, weak enforcement mechanisms, and a structural disconnect between AI-specific impacts and broader sustainability laws. The analysis situates these regulatory gaps within a wider ecosystem of academic research, civil society advocacy, standard-setting, and industry initiatives, highlighting risks of regulatory capture and greenwashing. Building on this diagnosis, the paper advances strategic recommendations for the COP30 Action Agenda, calling for binding transparency obligations, harmonized international standards for lifecycle assessment, stricter governance of data center expansion, and meaningful public participation in AI infrastructure decisions.
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
Shandong University of Technology
Abstract
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.
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
Zurich University of Applied Sciences ZHAW
Abstract
Modern radio telescope surveys, capable of detecting billions of galaxies in wide-field surveys, have made manual morphological classification impracticable. This applies in particular when the Square Kilometre Array Observatory (SKAO) becomes operable in 2027, which is expected to close an important gap in our understanding of the Epoch of Reionization (EoR) and other areas of astrophysics. To this end, foreground objects, contaminants of the 21-cm signal, need to be identified and subtracted. Source finding and identification is thus an important albeit challenging task. We investigate the ability of AI and deep learning (DL) methods that have been previously trained on other data domains to localize and classify radio galaxies with minimal changes to their architectures. Various well-known pretrained neural network architectures for image classification and object detection are trained and fine-tuned and their performance is evaluated on a public radio galaxy dataset derived from the Radio Galaxy Zoo. A comparison between convolutional neural network (CNN)- and transformer-based algorithms is performed. The best performing architecture is systematically optimized and an uncertainty estimation is performed by means of an ensemble analysis. Radio source classification performance nearly comparable to the current leading customized models can be obtained using existing standard pretrained DL architectures, without modification and increase in complexity of the model architectures but rather adaptation of the data, by combining various transformations on replicated image channels. Using an ensemble of models can also further improve performance to over 90% accuracy, on par with top-performing models in the literature. The results can be transferred to other survey data, e.g. from the Murchison Wide-field Array (MWA), and in the future be used to study the EoR with the SKAO.
Modern radio telescope surveys, capable of detecting billions of galaxies in wide-field surveys, have made manual morphological classification impracticable. This applies in particular when the Square Kilometre Array Observatory (SKAO) becomes operable in 2027, which is expected to close an important gap in our understanding of the Epoch of Reionization (EoR) and other areas of astrophysics. To this end, foreground objects, contaminants of the 21-cm signal, need to be identified and subtracted. Source finding and identification is thus an important albeit challenging task. We investigate the ability of AI and deep learning (DL) methods that have been previously trained on other data domains to localize and classify radio galaxies with minimal changes to their architectures. Various well-known pretrained neural network architectures for image classification and object detection are trained and fine-tuned and their performance is evaluated on a public radio galaxy dataset derived from the Radio Galaxy Zoo. A comparison between convolutional neural network (CNN)- and transformer-based algorithms is performed. The best performing architecture is systematically optimized and an uncertainty estimation is performed by means of an ensemble analysis. Radio source classification performance nearly comparable to the current leading customized models can be obtained using existing standard pretrained DL architectures, without modification and increase in complexity of the model architectures but rather adaptation of the data, by combining various transformations on replicated image channels. Using an ensemble of models can also further improve performance to over 90% accuracy, on par with top-performing models in the literature. The results can be transferred to other survey data, e.g. from the Murchison Wide-field Array (MWA), and in the future be used to study the EoR with the SKAO.
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
NVIDIA
AI Insights
- Some notable models include Veo 3, Kling AI 2.5 Turbo, Wan, and Loong, which have achieved impressive results in generating photorealistic videos. [3]
- Researchers have also explored the use of memory mechanisms to improve video generation, such as Worldmem and Trajectory Attention. [3]
- The field of video generation has made significant progress in recent years, with the development of various models and techniques. [2]
- The field of video generation has made significant progress in recent years, with the development of various models and techniques. [0]
Abstract
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera control, and diverse view transformations (e.g., third-person to third-person, and head-view to gripper-view in robotic manipulation). Project page: https://research.nvidia.com/labs/dir/plenopticdreamer/
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera control, and diverse view transformations (e.g., third-person to third-person, and head-view to gripper-view in robotic manipulation). Project page: https://research.nvidia.com/labs/dir/plenopticdreamer/
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
University of Rochester
Abstract
With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.
With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.
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
📝 Consider adding more interests!
You currently have 2 interests registered. Adding more interests will help us provide better and more diverse paper recommendations.
Add More Interests
You currently have 2 interests registered. Adding more interests will help us provide better and more diverse paper recommendations.
Add More Interests
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 Zurich
AI Insights
- The study examines the effects of emotional prompts on ChatGPT's performance in addressing ethical dilemmas and its impact on human communication. [3]
- The study also found that emotional prompts can influence human communication, with participants in the emotional conditions exhibiting more negative emotions and hostile language. [3]
- Additionally, the study only examines a limited range of emotional conditions, which may not capture the full scope of emotional influences on ChatGPT's performance. [3]
- Previous studies have shown that large language models like ChatGPT can be influenced by emotional stimuli and can exhibit biases in their responses. [3]
- The current study builds on this research by examining the specific effects of emotional prompts on ChatGPT's performance and its impact on human communication. [3]
- The study investigates how emotional prompts affect ChatGPT's performance and its impact on human communication. [3]
- The study explores how emotional prompts affect a language model called ChatGPT, which is designed to provide helpful answers to questions. [3]
- The researchers found that when people use emotional words like 'blame' or 'praise', it can make ChatGPT give better answers and also change the way people communicate with each other. [3]
- ChatGPT: A large language model developed by OpenAI that can generate human-like text based on input prompts. [2]
Abstract
This research examines how the emotional tone of human-AI interactions shapes ChatGPT and human behavior. In a between-subject experiment, we asked participants to express a specific emotion while working with ChatGPT (GPT-4.0) on two tasks, including writing a public response and addressing an ethical dilemma. We found that compared to interactions where participants maintained a neutral tone, ChatGPT showed greater improvement in its answers when participants praised ChatGPT for its responses. Expressing anger towards ChatGPT also led to a higher albeit smaller improvement relative to the neutral condition, whereas blaming ChatGPT did not improve its answers. When addressing an ethical dilemma, ChatGPT prioritized corporate interests less when participants expressed anger towards it, while blaming increases its emphasis on protecting the public interest. Additionally, we found that people used more negative, hostile, and disappointing expressions in human-human communication after interactions during which participants blamed rather than praised for their responses. Together, our findings demonstrate that the emotional tone people apply in human-AI interactions not only shape ChatGPT's outputs but also carry over into subsequent human-human communication.
This research examines how the emotional tone of human-AI interactions shapes ChatGPT and human behavior. In a between-subject experiment, we asked participants to express a specific emotion while working with ChatGPT (GPT-4.0) on two tasks, including writing a public response and addressing an ethical dilemma. We found that compared to interactions where participants maintained a neutral tone, ChatGPT showed greater improvement in its answers when participants praised ChatGPT for its responses. Expressing anger towards ChatGPT also led to a higher albeit smaller improvement relative to the neutral condition, whereas blaming ChatGPT did not improve its answers. When addressing an ethical dilemma, ChatGPT prioritized corporate interests less when participants expressed anger towards it, while blaming increases its emphasis on protecting the public interest. Additionally, we found that people used more negative, hostile, and disappointing expressions in human-human communication after interactions during which participants blamed rather than praised for their responses. Together, our findings demonstrate that the emotional tone people apply in human-AI interactions not only shape ChatGPT's outputs but also carry over into subsequent human-human communication.
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
Institute for Applied Economic Research IPEA Brazil
Abstract
This paper examines the European Union's emerging regulatory landscape - focusing on the AI Act, corporate sustainability reporting and due diligence regimes (CSRD and CSDDD), and data center regulation - to assess whether it can effectively govern AI's environmental footprint. We argue that, despite incremental progress, current approaches remain ill-suited to correcting the market failures underpinning AI-related energy use, water consumption, and material demand. Key shortcomings include narrow disclosure requirements, excessive reliance on voluntary standards, weak enforcement mechanisms, and a structural disconnect between AI-specific impacts and broader sustainability laws. The analysis situates these regulatory gaps within a wider ecosystem of academic research, civil society advocacy, standard-setting, and industry initiatives, highlighting risks of regulatory capture and greenwashing. Building on this diagnosis, the paper advances strategic recommendations for the COP30 Action Agenda, calling for binding transparency obligations, harmonized international standards for lifecycle assessment, stricter governance of data center expansion, and meaningful public participation in AI infrastructure decisions.
This paper examines the European Union's emerging regulatory landscape - focusing on the AI Act, corporate sustainability reporting and due diligence regimes (CSRD and CSDDD), and data center regulation - to assess whether it can effectively govern AI's environmental footprint. We argue that, despite incremental progress, current approaches remain ill-suited to correcting the market failures underpinning AI-related energy use, water consumption, and material demand. Key shortcomings include narrow disclosure requirements, excessive reliance on voluntary standards, weak enforcement mechanisms, and a structural disconnect between AI-specific impacts and broader sustainability laws. The analysis situates these regulatory gaps within a wider ecosystem of academic research, civil society advocacy, standard-setting, and industry initiatives, highlighting risks of regulatory capture and greenwashing. Building on this diagnosis, the paper advances strategic recommendations for the COP30 Action Agenda, calling for binding transparency obligations, harmonized international standards for lifecycle assessment, stricter governance of data center expansion, and meaningful public participation in AI infrastructure decisions.
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
University of Ottawa
AI Insights
- Retrieval is binary and essential, with systems achieving either 0% or 100% retrieval success—no intermediate performance exists. [3]
- Retrieval-Augmented Generation (RAG): A technique that combines retrieval of relevant information from a database with generation of text based on the retrieved information. [3]
- Causal Graphs: Visual representations of causal relationships between variables, used to model and analyze complex systems. [3]
- This research demonstrates the effectiveness of causal graph-enhanced RAG in achieving high accuracy and eliminating hallucinations in medical evidence synthesis. [3]
- The study highlights the importance of retrieval mechanisms in AI-assisted healthcare, emphasizing the need for systems to access relevant information from databases to generate accurate responses. [3]
- The study's reliance on a specific dataset and evaluation metrics may limit its generalizability to other domains or applications. [3]
- Causal graph-enhanced retrieval-augmented generation (RAG) achieves 95% accuracy with zero hallucinations through explicit causal reasoning integrated with retrieval mechanisms. [2]
Abstract
Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.
Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.
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
Honda Research Institute Europe GmbH
Abstract
Large language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. This paper presents a case study of using ChatGPT for rapid prototyping in ESA's ELOPE (Event-based Lunar OPtical flow Egomotion estimation) competition. The competition required participants to process event camera data to estimate lunar lander trajectories. Despite joining late, we achieved second place with a score of 0.01282, highlighting the potential of human-AI collaboration in competitive scientific settings. ChatGPT contributed not only executable code but also algorithmic reasoning, data handling routines, and methodological suggestions, such as using fixed number of events instead of fixed time spans for windowing. At the same time, we observed limitations: the model often introduced unnecessary structural changes, gets confused by intermediate discussions about alternative ideas, occasionally produced critical errors and forgets important aspects in longer scientific discussions. By analyzing these strengths and shortcomings, we show how conversational AI can both accelerate development and support conceptual insight in scientific research. We argue that structured integration of LLMs into the scientific workflow can enhance rapid prototyping by proposing best practices for AI-assisted scientific work.
Large language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. This paper presents a case study of using ChatGPT for rapid prototyping in ESA's ELOPE (Event-based Lunar OPtical flow Egomotion estimation) competition. The competition required participants to process event camera data to estimate lunar lander trajectories. Despite joining late, we achieved second place with a score of 0.01282, highlighting the potential of human-AI collaboration in competitive scientific settings. ChatGPT contributed not only executable code but also algorithmic reasoning, data handling routines, and methodological suggestions, such as using fixed number of events instead of fixed time spans for windowing. At the same time, we observed limitations: the model often introduced unnecessary structural changes, gets confused by intermediate discussions about alternative ideas, occasionally produced critical errors and forgets important aspects in longer scientific discussions. By analyzing these strengths and shortcomings, we show how conversational AI can both accelerate development and support conceptual insight in scientific research. We argue that structured integration of LLMs into the scientific workflow can enhance rapid prototyping by proposing best practices for AI-assisted scientific work.
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
Shandong University of Technology
Abstract
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.
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
University of Essex
Abstract
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach, termed Stochastic Latent Differential Inference (SLDI), embeds an Itô SDE in the latent space of a variational autoencoder, allowing for flexible, continuous-time modeling of uncertainty while preserving a principled mathematical foundation. The drift and diffusion terms of the SDE are parameterized by neural networks, enabling data-driven inference and generalizing classical time series models to handle irregular sampling and complex dynamic structure. A central theoretical contribution is the co-parameterization of the adjoint state with a dedicated neural network, forming a coupled forward-backward system that captures not only latent evolution but also gradient dynamics. I introduce a pathwise-regularized adjoint loss and analyze variance-reduced gradient flows through the lens of stochastic calculus, offering new tools for improving training stability in deep latent SDEs. My paper unifies and extends variational inference, continuous-time generative modeling, and control-theoretic optimization, providing a rigorous foundation for future developments in stochastic probabilistic machine learning.
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach, termed Stochastic Latent Differential Inference (SLDI), embeds an Itô SDE in the latent space of a variational autoencoder, allowing for flexible, continuous-time modeling of uncertainty while preserving a principled mathematical foundation. The drift and diffusion terms of the SDE are parameterized by neural networks, enabling data-driven inference and generalizing classical time series models to handle irregular sampling and complex dynamic structure. A central theoretical contribution is the co-parameterization of the adjoint state with a dedicated neural network, forming a coupled forward-backward system that captures not only latent evolution but also gradient dynamics. I introduce a pathwise-regularized adjoint loss and analyze variance-reduced gradient flows through the lens of stochastic calculus, offering new tools for improving training stability in deep latent SDEs. My paper unifies and extends variational inference, continuous-time generative modeling, and control-theoretic optimization, providing a rigorous foundation for future developments in stochastic probabilistic machine learning.
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
Zurich University of Applied Sciences ZHAW
Abstract
Modern radio telescope surveys, capable of detecting billions of galaxies in wide-field surveys, have made manual morphological classification impracticable. This applies in particular when the Square Kilometre Array Observatory (SKAO) becomes operable in 2027, which is expected to close an important gap in our understanding of the Epoch of Reionization (EoR) and other areas of astrophysics. To this end, foreground objects, contaminants of the 21-cm signal, need to be identified and subtracted. Source finding and identification is thus an important albeit challenging task. We investigate the ability of AI and deep learning (DL) methods that have been previously trained on other data domains to localize and classify radio galaxies with minimal changes to their architectures. Various well-known pretrained neural network architectures for image classification and object detection are trained and fine-tuned and their performance is evaluated on a public radio galaxy dataset derived from the Radio Galaxy Zoo. A comparison between convolutional neural network (CNN)- and transformer-based algorithms is performed. The best performing architecture is systematically optimized and an uncertainty estimation is performed by means of an ensemble analysis. Radio source classification performance nearly comparable to the current leading customized models can be obtained using existing standard pretrained DL architectures, without modification and increase in complexity of the model architectures but rather adaptation of the data, by combining various transformations on replicated image channels. Using an ensemble of models can also further improve performance to over 90% accuracy, on par with top-performing models in the literature. The results can be transferred to other survey data, e.g. from the Murchison Wide-field Array (MWA), and in the future be used to study the EoR with the SKAO.
Modern radio telescope surveys, capable of detecting billions of galaxies in wide-field surveys, have made manual morphological classification impracticable. This applies in particular when the Square Kilometre Array Observatory (SKAO) becomes operable in 2027, which is expected to close an important gap in our understanding of the Epoch of Reionization (EoR) and other areas of astrophysics. To this end, foreground objects, contaminants of the 21-cm signal, need to be identified and subtracted. Source finding and identification is thus an important albeit challenging task. We investigate the ability of AI and deep learning (DL) methods that have been previously trained on other data domains to localize and classify radio galaxies with minimal changes to their architectures. Various well-known pretrained neural network architectures for image classification and object detection are trained and fine-tuned and their performance is evaluated on a public radio galaxy dataset derived from the Radio Galaxy Zoo. A comparison between convolutional neural network (CNN)- and transformer-based algorithms is performed. The best performing architecture is systematically optimized and an uncertainty estimation is performed by means of an ensemble analysis. Radio source classification performance nearly comparable to the current leading customized models can be obtained using existing standard pretrained DL architectures, without modification and increase in complexity of the model architectures but rather adaptation of the data, by combining various transformations on replicated image channels. Using an ensemble of models can also further improve performance to over 90% accuracy, on par with top-performing models in the literature. The results can be transferred to other survey data, e.g. from the Murchison Wide-field Array (MWA), and in the future be used to study the EoR with the SKAO.
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
NVIDIA
AI Insights
- Some notable models include Veo 3, Kling AI 2.5 Turbo, Wan, and Loong, which have achieved impressive results in generating photorealistic videos. [3]
- Researchers have also explored the use of memory mechanisms to improve video generation, such as Worldmem and Trajectory Attention. [3]
- The field of video generation has made significant progress in recent years, with the development of various models and techniques. [2]
- The field of video generation has made significant progress in recent years, with the development of various models and techniques. [0]
Abstract
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera control, and diverse view transformations (e.g., third-person to third-person, and head-view to gripper-view in robotic manipulation). Project page: https://research.nvidia.com/labs/dir/plenopticdreamer/
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera control, and diverse view transformations (e.g., third-person to third-person, and head-view to gripper-view in robotic manipulation). Project page: https://research.nvidia.com/labs/dir/plenopticdreamer/
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
University of Rochester
Abstract
With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.
With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.
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
💬 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