AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDiaVLo: Diagnosing Behaviours of Vision-Language Models
arXiv:2609.22008v1 Announce Type: cross Abstract: Vision-language models (VLMs) rely on storing and transferring appropriate information across their sub-components. Verifying that the VLMs exhibit desired behaviours, wh…
- arXiv cs.AIresearchGricea: An Open Science Platform for Conversational AI Research
arXiv:2609.22039v1 Announce Type: cross Abstract: We need studies on conversational AI (CAI) at scale to understand human behavior and shape CAI design. However, fragmented reporting of systems and study configurations h…
- arXiv cs.AIresearchCollab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programming
arXiv:2508.03030v3 Announce Type: replace Abstract: Mixed-integer linear programming (MILP) has been a fundamental problem in combinatorial optimization. Conventional MILP solving mainly relies on carefully designed heur…
- arXiv cs.AIresearchFact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration
arXiv:2509.25252v3 Announce Type: replace Abstract: "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." Large Language Models have conquered natural language but remain prisoners of their…
- arXiv cs.AIresearchMemeLens: Multilingual Multitask VLMs for Memes
arXiv:2601.12539v4 Announce Type: replace Abstract: Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Ex…
- arXiv cs.AIresearchBeyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation
arXiv:2603.13099v3 Announce Type: replace Abstract: We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning throu…
- arXiv cs.AIresearchTransferable knowledge graphs with executable learned operators for algorithm design
arXiv:2603.27922v2 Announce Type: replace Abstract: Procedural knowledge in algorithm design is embedded in source code and rebuilt for each new domain. We introduce Generative Executable Algorithm Knowledge Graphs (GEAK…
- arXiv cs.AIresearchBoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
arXiv:2605.09134v4 Announce Type: replace Abstract: Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We pres…
- arXiv cs.AIresearchOn the Limitations of Large Language Models for Conceptual Database Modeling
arXiv:2605.11986v2 Announce Type: replace Abstract: This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-…
- arXiv cs.AIresearchA Forced-Structure Reduction and Verifiable Bounds for Conway's 99-Graph
arXiv:2608.11211v2 Announce Type: replace Abstract: Conway's 99-graph problem asks whether a strongly regular graph with parameters $\mathrm{srg}(99,14,1,2)$ exists. We develop two complementary lines of attack. Fixing o…
- arXiv cs.AIresearchBalance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison
arXiv:2608.30044v3 Announce Type: replace Abstract: Model comparison increasingly relies on large collections of publicly reported benchmark scores, yet common aggregation strategies trade off evidence coverage against c…
- arXiv cs.AIresearchFraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation
arXiv:2609.13519v2 Announce Type: replace Abstract: We introduce Fraglingo, an autoregressive molecular generator that constructs molecules step by step from chemically meaningful fragments connected through predefined a…
- arXiv cs.AIresearchReinforcement Learning under External Influence: Guarantees, Algorithms, and Sample Complexity
arXiv:2305.16056v5 Announce Type: replace-cross Abstract: In this paper, we study the problem of reinforcement learning under the influence of external events. For this, we consider Markov decision processes with continu…
- arXiv cs.AIresearchSoda: An Object-Oriented Functional Language for Specifying Human-Centered Problems
arXiv:2310.01961v3 Announce Type: replace-cross Abstract: We present Soda (Symbolic Objective Descriptive Analysis), a language that helps to treat qualities and quantities in a natural way and greatly simplifies the tas…
- arXiv cs.AIresearchContinuous Spiking Graph Neural Networks
arXiv:2404.01897v3 Announce Type: replace-cross Abstract: Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural networks (GNNs) by…
- arXiv cs.AIresearchUnderstanding In-context Learning of Addition via Activation Subspaces
arXiv:2505.05145v4 Announce Type: replace-cross Abstract: To perform few-shot learning, language models extract signals from a few input-label pairs, aggregate them into a learned prediction rule, and apply this rule to…
- arXiv cs.AIresearchGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions
arXiv:2509.10303v3 Announce Type: replace-cross Abstract: Online reinforcement learning (RL) approaches have demonstrated strong performance on Job Shop Scheduling (JSP) and Flexible JSP (FJSP) problems by learning sched…
- arXiv cs.AIresearchAuditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5
arXiv:2510.07024v4 Announce Type: replace-cross Abstract: LLMs are remarkable artifacts that have revolutionized a range of knowledge-intensive tasks. A significant contributor is their factual knowledge, which, to date,…
- arXiv cs.AIresearchThe Impact of Semantic Pairs on Self-Supervised Representation Learning
arXiv:2510.08722v4 Announce Type: replace-cross Abstract: Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this encourages invariance…
- arXiv cs.AIresearchDeep Learning-Enhanced Real-Time Wi-Fi Sensing Through Single Transceiver Pair
arXiv:2511.02845v4 Announce Type: replace-cross Abstract: The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticated applications. In r…
- arXiv cs.AIresearchUnderstanding Structural Representation in Foundation Models for Polymers
arXiv:2512.11881v2 Announce Type: replace-cross Abstract: From the relative scarcity of training data to the lack of standardized benchmarks, the creation of effective foundation models for polymers faces significant and…
- arXiv cs.AIresearchLarge Language Models As Shannon Lossy Compressors Not Solomonoff Induction Estimators: The Singularity Is Not Near Without Symbolic Model Synthesis
arXiv:2601.05280v5 Announce Type: replace-cross Abstract: On the one hand, the question of whether Large Language Models (LLMs) are Solomonoff induction estimators has become an explicit question at the intersection of A…
- arXiv cs.AIresearchBEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis
arXiv:2601.07316v2 Announce Type: replace-cross Abstract: Automated electrocardiogram diagnosis using deep learning remains limited by signal-agnostic representations that treat multi-lead recordings as undifferentiated…
- arXiv cs.AIresearchMENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
arXiv:2602.07036v2 Announce Type: replace-cross Abstract: Audio large language models (AudioLLMs) enable instruction following over speech and general audio, but progress is limited by the scarcity of diverse, conversati…
- arXiv cs.AIresearchPosition: A Dynamical Systems Perspective is Needed to Advance Time Series Modeling
arXiv:2602.16864v3 Announce Type: replace-cross Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a lot of hype a…
- arXiv cs.AIresearchThe MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction
arXiv:2603.01250v4 Announce Type: replace-cross Abstract: Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magneti…
- arXiv cs.AIresearchTaming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning
arXiv:2603.12110v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) policies trained in simulation often degrade once deployed on real systems, where the controller must reject external disturbances tha…
- arXiv cs.AIresearchTowards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation
arXiv:2603.16086v2 Announce Type: replace-cross Abstract: While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively…
- arXiv cs.AIresearchHow do LLMs Compute Verbal Confidence
arXiv:2603.17839v4 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. Ho…
- arXiv cs.AIresearchEvolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems
arXiv:2604.07799v3 Announce Type: replace-cross Abstract: Robots deployed for long periods keep improving their skills, and each update changes a released system. We treat this as a software-lifecycle problem: a fixed de…
- arXiv cs.AIresearchLessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation
arXiv:2604.08797v2 Announce Type: replace-cross Abstract: Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual s…
- arXiv cs.AIresearchRepresentation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization
arXiv:2604.16775v3 Announce Type: replace-cross Abstract: Generative medical event models use tokenized sequences of patient timelines as input, but practical guidance on the many decisions around tokenization is limited…
- arXiv cs.AIresearchDiagnostic-Guided Longitudinal Modeling for Forecasting Retinal Atrophy Progression
arXiv:2604.16955v3 Announce Type: replace-cross Abstract: Stochastic generative models are increasingly used for longitudinal imaging, but their added complexity may provide limited benefit when predictable disease-relat…
- arXiv cs.AIresearchHow a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models
arXiv:2604.27167v4 Announce Type: replace-cross Abstract: On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation…
- arXiv cs.AIresearchWhy Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
arXiv:2605.00226v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymaking. While L…
- arXiv cs.AIresearchREALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception
arXiv:2605.00271v4 Announce Type: replace-cross Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme ligh…
- arXiv cs.AIresearchRhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI
arXiv:2605.01240v3 Announce Type: replace-cross Abstract: Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored.…
- arXiv cs.AIresearchLiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
arXiv:2605.09384v2 Announce Type: replace-cross Abstract: The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2-4B p…
- arXiv cs.AIresearchThe critical slowing down in training diffusion models
arXiv:2605.12597v3 Announce Type: replace-cross Abstract: Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled major advances,…
- arXiv cs.AIresearchRevisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
arXiv:2605.12969v5 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reasoning tasks. We first s…
- arXiv cs.AIresearchPaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
arXiv:2606.00515v2 Announce Type: replace-cross Abstract: Contact-rich manipulation demands both high-level semantic reasoning and the safe regulation of high-frequency contact dynamics. While Vision-Language-Action (VLA…
- arXiv cs.AIresearchScaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
arXiv:2606.04287v2 Announce Type: replace-cross Abstract: Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond.…
- arXiv cs.AIresearchLearning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications
arXiv:2607.00442v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that may limit interpretability of le…
- arXiv cs.AIresearchGeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation
arXiv:2607.03869v2 Announce Type: replace-cross Abstract: Referring remote sensing image segmentation segments the object named by a natural-language expression in an aerial image. Existing training-free methods resolve…
- arXiv cs.AIresearchCover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
arXiv:2607.13571v2 Announce Type: replace-cross Abstract: Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments wh…
- arXiv cs.AIresearchTeaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
arXiv:2607.21971v2 Announce Type: replace-cross Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize t…
- arXiv cs.AIresearchSixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct
arXiv:2608.00285v2 Announce Type: replace-cross Abstract: Sixteen language models drawn from ten families produced, on average, the semantic diversity of 1.69 distinct formulations of a psychotherapeutic case, against a…
- arXiv cs.AIresearchAre You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
arXiv:2608.13430v2 Announce Type: replace-cross Abstract: Instruction-tuned language models achieve strong performance across a range of generation tasks but have recently been shown to exhibit verbalized overconfidence,…
- arXiv cs.AIresearchMulti-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
arXiv:2608.17605v2 Announce Type: replace-cross Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, in…
- arXiv cs.AIresearchSelf-Explanation Tutor for Active Study of CS1 Worked Examples
arXiv:2608.25180v2 Announce Type: replace-cross Abstract: Worked examples are an important part of introductory programming, but reading their expert explanations is passive. Self explanation, students explaining the pro…