Why we think this paper is great for you:
This paper directly applies LLMs to enhance product search, offering valuable insights into leveraging AI for core product features and improving user experience in e-commerce.

Abstract
Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these expressions in e-commerce queries through a framework that extracts structured interpretations or hints. Our approach decomposes queries into attribute-value hints generated concurrently with retrieval, enabling efficient integration into the ranking pipeline. Our method improves search performanc eby 10.9 points in MAP and ranking by 5.9 points in MRR over baselines. Since direct LLM-based reranking faces prohibitive latency, we develop an efficient approach transferring superlative interpretations to lightweight models. Our findings provide insights into how superlative semantics can be represented and transferred between models, advancing linguistic interpretation in retrieval systems while addressing practical deployment constraints.

AI Summary

• The proposed hint-augmented re-ranking framework significantly improves e-commerce search performance for superlative queries, achieving a 10.9 point increase in MAP and 5.9 points in MRR over baselines. [3]
• LLMs can efficiently uncover latent intent in superlative e-commerce queries by decomposing them into structured attribute-value 'hints' (reasoning, brands, features, generated queries). [3]
• Hint generation can be executed concurrently with retrieval, introducing minimal end-to-end latency overhead (e.g., 3.5% for 0.5B model) and making the system practical for high-traffic environments. [3]
• A specialized, large-scale dataset of 21k superlative queries and 470k products was curated, addressing the scarcity of such data in existing information retrieval benchmarks. [3]
• Hints: Structured interpretations extracted from LLMs that decompose superlative terms in queries into attribute-value pairs, including reasoning, suggested brands, key features, and alternative query formulations. [3]
• Hint-Augmented Re-ranking: A framework where LLM-generated hints are used to guide and enhance lightweight re-ranking systems, improving their ability to interpret and respond to superlative queries. [3]
• Superlative Queries: Search queries containing comparative expressions (e.g., 'best', 'most popular') that implicitly require the search engine to perform multi-dimensional evaluation and apply domain-specific knowledge. [3]
• The approach enables the transfer of complex superlative interpretations from large language models (LLMs) to lightweight models, addressing prohibitive latency constraints for real-time deployment. [2]
• Small language models (SLMs) with hint augmentation can surpass the ranking performance of much larger, listwise LLM rerankers while being orders of magnitude more computationally efficient (e.g., 0.5B+H model outperforms 72B model by 21.4 P@1). [2]
• Human evaluation confirms that the hint-augmented system significantly outperforms the baseline, with a 65.38% win rate, validating the effectiveness of transferring LLM knowledge for improved relevance. [2]

Why we think this paper is great for you:
Exploring creativity evaluation across the entire product lifecycle using MLLMs, this paper provides crucial perspectives for integrating AI into your product development and innovation processes.

Abstract
Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. The absence of an existing benchmark further exacerbates this dilemma. To this end, we propose CreBench, which consists of two key components: 1) an evaluation benchmark covering the multiple dimensions from creative idea to process to products; 2) CreMIT (Creativity Multimodal Instruction Tuning dataset), a multimodal creativity evaluation dataset, consisting of 2.2K diverse-sourced multimodal data, 79.2K human feedbacks and 4.7M multi-typed instructions. Specifically, to ensure MLLMs can handle diverse creativity-related queries, we prompt GPT to refine these human feedbacks to activate stronger creativity assessment capabilities. CreBench serves as a foundation for building MLLMs that understand human-aligned creativity. Based on the CreBench, we fine-tune open-source general MLLMs, resulting in CreExpert, a multimodal creativity evaluation expert model. Extensive experiments demonstrate that the proposed CreExpert models achieve significantly better alignment with human creativity evaluation compared to state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision.

Why we think this paper is great for you:
This paper demonstrates how industrial AI can enhance decision support in various management phases, offering a robust framework for applying AI in strategic planning and operational management.

Abstract
The construction industry is presently going through a transformation led by adopting digital technologies that leverage Artificial Intelligence (AI). These industrial AI solutions assist in various phases of the construction process, including planning, design, production and management. In particular, the production phase offers unique potential for the integration of such AI-based solutions. These AI-based solutions assist site managers, project engineers, coordinators and other key roles in making final decisions. To facilitate the decision-making process in the production phase of construction through a human-centric AI-based solution, it is important to understand the needs and challenges faced by the end users who interact with these AI-based solutions to enhance the effectiveness and usability of these systems. Without this understanding, the potential usage of these AI-based solutions may be limited. Hence, the purpose of this research study is to explore, identify and describe the key factors crucial for developing AI solutions in the construction industry. This study further identifies the correlation between these key factors. This was done by developing a demonstrator and collecting quantifiable feedback through a questionnaire targeting the end users, such as site managers and construction professionals. This research study will offer insights into developing and improving these industrial AI solutions, focusing on Human-System Interaction aspects to enhance decision support, usability, and overall AI solution adoption.

Why we think this paper is great for you:
This paper critically examines how LLMs are fundamentally reshaping organizational knowledge, which is essential for you to set a clear vision and develop robust product strategies in an evolving tech landscape.

Abstract
Large Language Models (LLMs) are reshaping organizational knowing by unsettling the epistemological foundations of representational and practice-based perspectives. We conceptualize LLMs as Haraway-ian monsters, that is, hybrid, boundary-crossing entities that destabilize established categories while opening new possibilities for inquiry. Focusing on analogizing as a fundamental driver of knowledge, we examine how LLMs generate connections through large-scale statistical inference. Analyzing their operation across the dimensions of surface/deep analogies and near/far domains, we highlight both their capacity to expand organizational knowing and the epistemic risks they introduce. Building on this, we identify three challenges of living with such epistemic monsters: the transformation of inquiry, the growing need for dialogical vetting, and the redistribution of agency. By foregrounding the entangled dynamics of knowing-with-LLMs, the paper extends organizational theory beyond human-centered epistemologies and invites renewed attention to how knowledge is created, validated, and acted upon in the age of intelligent technologies.

Why we think this paper is great for you:
Addressing critical risks and trustworthiness in AI applications, this paper provides essential considerations for managing the lifecycle and roadmap of your AI products responsibly.

Abstract
Risks associated with the use of AI, ranging from algorithmic bias to model hallucinations, have received much attention and extensive research across the AI community, from researchers to end-users. However, a gap exists in the systematic assessment of supply chain risks associated with the complex web of data sources, pre-trained models, agents, services, and other systems that contribute to the output of modern AI systems. This gap is particularly problematic when AI systems are used in critical applications, such as the food supply, healthcare, utilities, law, insurance, and transport. We survey the current state of AI risk assessment and management, with a focus on the supply chain of AI and risks relating to the behavior and outputs of the AI system. We then present a proposed taxonomy specifically for categorizing AI supply chain entities. This taxonomy helps stakeholders, especially those without extensive AI expertise, to "consider the right questions" and systematically inventory dependencies across their organization's AI systems. Our contribution bridges a gap between the current state of AI governance and the urgent need for actionable risk assessment and management of AI use in critical applications.

Why we think this paper is great for you:
This paper explores advanced embodied AI perception systems, which could inform your long-term product vision and roadmap for future AI products involving sophisticated visual capabilities.

Abstract
In embodied AI perception systems, visual perception should be active: the goal is not to passively process static images, but to actively acquire more informative data within pixel and spatial budget constraints. Existing vision models and fixed RGB-D camera systems fundamentally fail to reconcile wide-area coverage with fine-grained detail acquisition, severely limiting their efficacy in open-world robotic applications. To address this issue, we propose EyeVLA, a robotic eyeball for active visual perception that can take proactive actions based on instructions, enabling clear observation of fine-grained target objects and detailed information across a wide spatial extent. EyeVLA discretizes action behaviors into action tokens and integrates them with vision-language models (VLMs) that possess strong open-world understanding capabilities, enabling joint modeling of vision, language, and actions within a single autoregressive sequence. By using the 2D bounding box coordinates to guide the reasoning chain and applying reinforcement learning to refine the viewpoint selection policy, we transfer the open-world scene understanding capability of the VLM to a vision language action (VLA) policy using only minimal real-world data. Experiments show that our system efficiently performs instructed scenes in real-world environments and actively acquires more accurate visual information through instruction-driven actions of rotation and zoom, thereby achieving strong environmental perception capabilities. EyeVLA introduces a novel robotic vision system that leverages detailed and spatially rich, large-scale embodied data, and actively acquires highly informative visual observations for downstream embodied tasks.

Why we think this paper is great for you:
This research on AI modeling of human cognitive development offers foundational insights into user behavior and learning, potentially informing your product design and strategy for AI-powered analytical or educational tools.

Abstract
Mathematical thinking is a fundamental aspect of human cognition. Cognitive scientists have investigated the mechanisms that underlie our ability to thinking geometrically and numerically, to take two prominent examples, and developmental scientists have documented the trajectories of these abilities over the lifespan. Prior research has shown that computer vision (CV) models trained on the unrelated task of image classification nevertheless learn latent representations of geometric and numerical concepts similar to those of adults. Building on this demonstrated cognitive alignment, the current study investigates whether CV models also show developmental alignment: whether their performance improvements across training to match the developmental progressions observed in children. In a detailed case study of the ResNet-50 model, we show that this is the case. For the case of geometry and topology, we find developmental alignment for some classes of concepts (Euclidean Geometry, Geometrical Figures, Metric Properties, Topology) but not others (Chiral Figures, Geometric Transformations, Symmetrical Figures). For the case of number, we find developmental alignment in the emergence of a human-like ``mental number line'' representation with experience. These findings show the promise of computer vision models for understanding the development of mathematical understanding in humans. They point the way to future research exploring additional model architectures and building larger benchmarks.