AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchVisuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
arXiv:2609.24906v1 Announce Type: cross Abstract: Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In this work, we focus on pruning of modern planar tree tra…
- arXiv cs.AIresearchExactness at Inference: A Representational Criterion for Out-of-Distribution Generalization
arXiv:2609.24942v1 Announce Type: cross Abstract: A model generalizes outside its training distribution only when it computes a representation structurally equivalent to the generating mechanism, not an approximation fit…
- arXiv cs.AIresearchGenerative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks
arXiv:2609.24955v1 Announce Type: cross Abstract: Visual instructions for physical tasks are typically authored in one context and followed in another, requiring users to translate demonstrated tools, materials, and spat…
- arXiv cs.AIresearchDexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation
arXiv:2609.24976v1 Announce Type: cross Abstract: Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple predictive video world m…
- arXiv cs.AIresearchWorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
arXiv:2609.24984v1 Announce Type: cross Abstract: Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present…
- arXiv cs.AIresearchGameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
arXiv:2609.25001v2 Announce Type: replace-cross Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, and precise…
- arXiv cs.AIresearchSubgoal Search For Complex Reasoning Tasks
arXiv:2108.11204v4 Announce Type: replace Abstract: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) m…
- arXiv cs.AIresearchRL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner
arXiv:2410.23912v3 Announce Type: replace Abstract: The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, t…
- arXiv cs.AIresearchFairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions
arXiv:2412.00606v3 Announce Type: replace Abstract: Biases in automated clinical decision-making using Electronic Healthcare Records (EHR) impose significant disparities in patient care and treatment outcomes. Convention…
- arXiv cs.AIresearchMemory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
arXiv:2510.21175v2 Announce Type: replace Abstract: Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range of real-world tasks…
- arXiv cs.AIresearchChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry
arXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often relying on simple image…
- arXiv cs.AIresearchCARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
arXiv:2601.06352v3 Announce Type: replace Abstract: Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployment. We present CARD,…
- arXiv cs.AIresearchDo Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
arXiv:2601.06362v3 Announce Type: replace Abstract: Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characte…
- arXiv cs.AIresearchVeRA: Renewing Reasoning Benchmarks with Executable Specifications
arXiv:2602.13217v2 Announce Type: replace Abstract: Reasoning benchmarks need renewal along two axes: freshness and headroom. VeRA makes both executable and auditable by turning each item into a task family: a natural-la…
- arXiv cs.AIresearchWhen can we trust untrusted monitoring? A safety case sketch across collusion strategies
arXiv:2602.20628v2 Announce Type: replace Abstract: AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrus…
- arXiv cs.AIresearchSocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
arXiv:2603.16859v3 Announce Type: replace Abstract: Evaluating omni-modal large language models (OLMs) in multi-party dialogue requires more than answer correctness on pre-segmented inputs. We introduce SocialOmni, an of…
- arXiv cs.AIresearchToward an automated science of the mind
arXiv:2603.20988v2 Announce Type: replace Abstract: Artificial Intelligence is starting to automate scientific discovery, raising the prospect of an automated science of the mind. We chart this field around four challeng…
- arXiv cs.AIresearchCharacterizing Model-Native Skills
arXiv:2604.17614v2 Announce Type: replace Abstract: Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterizations rely on human-written tax…
- arXiv cs.AIresearchInformation-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems
arXiv:2604.24083v2 Announce Type: replace Abstract: Runtime monitoring of stochastic systems must distinguish nominal distributional relaxation from regime departure while controlling repeated-test false alarms under exp…
- arXiv cs.AIresearchTaming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances
arXiv:2604.27927v2 Announce Type: replace Abstract: We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS) and use it to show that sever…
- arXiv cs.AIresearchRankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking
arXiv:2605.11151v4 Announce Type: replace Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is…
- arXiv cs.AIresearchTTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
arXiv:2605.16638v2 Announce Type: replace Abstract: Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradigm, a generative…
- arXiv cs.AIresearchRubric-Guided Process Reward for Stepwise Model Routing
arXiv:2605.29310v2 Announce Type: replace Abstract: Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing a…
- arXiv cs.AIresearchRedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
arXiv:2606.06256v4 Announce Type: replace Abstract: As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory ca…
- arXiv cs.AIresearchA General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Data
arXiv:2606.28798v2 Announce Type: replace Abstract: The main objective of this paper is to propose a general framework for prediction based on different sources of multimodal data in the healthcare domain. We evaluated w…
- arXiv cs.AIresearchLength Penalties Make Chain-of-Thought Less Monitorable
arXiv:2607.09786v4 Announce Type: replace Abstract: Recent work trains reasoning models with length penalties to curb overthinking and cut inference cost. We show that these penalties make the chain of thought less monit…
- arXiv cs.AIresearchThe Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections
arXiv:2608.03921v3 Announce Type: replace Abstract: We reinterpret Transformer inference by developing a functionally equivalent mechanical-structural description of its functional architecture. Parameterized transformat…
- arXiv cs.AIresearchRegime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
arXiv:2608.14089v3 Announce Type: replace Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's…
- arXiv cs.AIresearchParticipatory Moral AI Is Not Neutral: The Invisible Hand of Developers
arXiv:2608.14522v2 Announce Type: replace Abstract: As AI systems make more morally loaded decisions across society, one response has been moral preference elicitation. In this approach, researchers poll participants on…
- arXiv cs.AIresearchPairwise Ranking Outperforms Single-Action RL for Offline Explanation Selection: A Practical Lesson
arXiv:2608.18531v2 Announce Type: replace Abstract: Industrial explainable-recommendation systems built on LLMs incur a substantial serving cost: each request triggers an LLM generation, with latency in the hundreds of m…
- arXiv cs.AIresearchDiffusion Models and Concept Formation
arXiv:2609.13047v2 Announce Type: replace Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the lea…
- arXiv cs.AIresearchSynthetic Data in Marketing Research: How to Evaluate and When to Trust
arXiv:2609.13995v2 Announce Type: replace Abstract: Debate over synthetic data in marketing research has polarized between claims that large language models (LLMs) make human respondents obsolete and calls to avoid them…
- arXiv cs.AIresearchAppliedScientist: Automated Scientific Revision Through Iterative AI Reviewing
arXiv:2609.14738v2 Announce Type: replace Abstract: Automated reviewing systems are increasingly evaluated based on the quality of the reviews they produce. Yet a review is only useful if acting on it leads to a measurab…
- arXiv cs.AIresearchNoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities
arXiv:2609.15695v2 Announce Type: replace Abstract: Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains challenging. Exist…
- arXiv cs.AIresearchBeyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
arXiv:2609.15706v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean benchmarks and o…
- arXiv cs.AIresearchAre LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)
arXiv:2609.15727v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as user simulators, yet it remains unclear whether their predictions faithfully reproduce the evolving decisions of i…
- arXiv cs.AIresearchReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
arXiv:2609.16639v3 Announce Type: replace Abstract: Continual post-training of large multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in opposite directions.…
- arXiv cs.AIresearchBeyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition
arXiv:2609.16752v3 Announce Type: replace Abstract: Cognitive Field Theory describes cognition as memory-dressed collective dynamics, in which slow relaxation modes support a persistent cognitive field. By connecting non…
- arXiv cs.AIresearchReflective Policy Optimization
arXiv:2406.03678v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per upd…
- arXiv cs.AIresearchA Mathematical Framework and a Suite of Learning Techniques for Neural-Symbolic Systems
arXiv:2407.09693v3 Announce Type: replace-cross Abstract: The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic method…
- arXiv cs.AIresearchOptimal Symmetries in Binary Classification
arXiv:2408.08823v2 Announce Type: replace-cross Abstract: We develop a theoretical foundation for designing group-equivariant neural networks that align the choice of symmetries with the underlying probability distributi…
- arXiv cs.AIresearchStreaming Deep Reinforcement Learning Finally Works
arXiv:2410.14606v3 Announce Type: replace-cross Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streaming learning has…
- arXiv cs.AIresearchA Course Intelligence Platform for Higher Education: Lessons from AI-Assisted Course Evaluation
arXiv:2411.02455v3 Announce Type: replace-cross Abstract: The rapid adoption of generative AI has created new opportunities for teaching, learning, and quality assurance. Existing applications, however, remain largely st…
- arXiv cs.AIresearchHow Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning?
arXiv:2412.07813v5 Announce Type: replace-cross Abstract: To alleviate the training burden in federated learning while enhancing convergence speed, Split Federated Learning (SFL) has emerged as a promising approach by co…
- arXiv cs.AIresearchLogits are All We Need to Adapt Closed Models
arXiv:2502.06806v5 Announce Type: replace-cross Abstract: Many commercial Large Language Models (LLMs) are often closed-source, limiting developers to prompt tuning for aligning content generation with specific applicati…
- arXiv cs.AIresearchEnhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning
arXiv:2503.09020v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been widely adopted in commercial code completion engines, significantly enhancing coding efficiency and productivity. However,…
- arXiv cs.AIresearchDisassociating performance from compositional feature learning
arXiv:2505.09716v4 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and transfer them t…
- arXiv cs.AIresearchMMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments
arXiv:2505.12254v3 Announce Type: replace-cross Abstract: Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underrepresent dense pedes…
- arXiv cs.AIresearchExplain Less, Understand More: Data-Efficient Personalization of Reader-Dependent Jargons
arXiv:2505.16227v4 Announce Type: replace-cross Abstract: Personalizing jargon detection and explanation is essential for making technical documents accessible to readers with diverse disciplinary backgrounds. However, t…
- arXiv cs.AIresearchLingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
arXiv:2506.07044v5 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datas…