AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
arXiv:2610.03710v1 Announce Type: cross Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physicall…
- arXiv cs.AIresearchWhat Should World Models Forget? Stratified Retention for Continual Adaptation
arXiv:2610.03713v1 Announce Type: cross Abstract: Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a co…
- arXiv cs.AIresearchLess Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
arXiv:2610.03717v1 Announce Type: cross Abstract: This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enablin…
- arXiv cs.AIresearchHeads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments
arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation does not imply that LL…
- arXiv cs.AIresearchOn the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode
arXiv:2603.13911v2 Announce Type: replace Abstract: A language model can give the wrong answer even when the correct answer is decodable from its intermediate states. To study this gap between decodability and selection,…
- arXiv cs.AIresearchGISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification
arXiv:2603.29112v2 Announce Type: replace Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems.…
- arXiv cs.AIresearchWhat's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
arXiv:2604.06995v3 Announce Type: replace Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based deci…
- arXiv cs.AIresearchWhat do your logits know?
arXiv:2604.09885v3 Announce Type: replace Abstract: Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses a risk of unintentional or mal…
- arXiv cs.AIresearchOffline Policy Optimization with Posterior Sampling
arXiv:2605.07393v2 Announce Type: replace Abstract: A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in ou…
- arXiv cs.AIresearchNARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities
arXiv:2605.12276v2 Announce Type: replace Abstract: Vector geospatial data represent the world as discrete geoentities, such as roads, buildings, and points of interest, each with semantic attributes, geometry, and spati…
- arXiv cs.AIresearchKGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning
arXiv:2605.14907v2 Announce Type: replace Abstract: Knowledge graph (KG) foundation models aim to generalize to graphs with unseen entities and relations by learning transferable relational structure. Most existing metho…
- arXiv cs.AIresearchRethinking RAG in Long Videos: What to Retrieve and How to Use It?
arXiv:2606.13141v2 Announce Type: replace Abstract: Retrieval-augmented generation is extending beyond text to long videos, where query-relevant chunks can be represented across multiple modalities and temporal granulari…
- arXiv cs.AIresearchMental-R1: Aligning LLM Reasoning for Mental Health Assessment
arXiv:2606.13176v2 Announce Type: replace Abstract: Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical for effective interven…
- arXiv cs.AIresearchA Multi-Timescale Recursive Self-Improvement Engine for Open-Ended Persona Growth
arXiv:2607.08252v2 Announce Type: replace Abstract: Role-playing AI personas today do not grow: they hold a fixed character, so the relationship a user builds with them has nothing to accumulate on. We introduce AutoPers…
- arXiv cs.AIresearchHow Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment
arXiv:2607.14197v2 Announce Type: replace Abstract: Artificial Intelligence (AI) answer engines now field a growing share of the questions that analysts, scholars, and the public ask about issues of peace and conflict. L…
- arXiv cs.AIresearchWAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation
arXiv:2608.22364v2 Announce Type: replace Abstract: World Action Models (WAMs) generate both future video and robot actions, offering two connected outputs for post-training supervision. How can a pretrained WAM learn fr…
- arXiv cs.AIresearchLearning transferable human physiology from two million hours of sleep with SleepFM-2
arXiv:2609.06849v2 Announce Type: replace Abstract: Sleep provides a nightly window into health by capturing coordinated activity across the brain, heart, muscles and respiratory system. We introduce SleepFM-2, a sleep f…
- arXiv cs.AIresearchLearning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
arXiv:2209.14887v3 Announce Type: replace-cross Abstract: Robotic locomotion is often approached with the goal of maximizing robustness and reactivity by increasing motion control frequency. We challenge this intuitive n…
- arXiv cs.AIresearchVIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models
arXiv:2311.18837v2 Announce Type: replace-cross Abstract: Diffusion models have achieved significant success in image and video generation. This motivates a growing interest in video editing tasks, where videos are edite…
- arXiv cs.AIresearchTowards Unified Music Emotion Recognition across Dimensional and Categorical Models
arXiv:2502.03979v3 Announce Type: replace-cross Abstract: One of the most significant challenges in Music Emotion Recognition (MER) comes from the fact that emotion labels can be heterogeneous across datasets with regard…
- arXiv cs.AIresearchHybrid Reasoning Systems That Prioritize and Enhance Human Intelligence
arXiv:2504.13477v3 Announce Type: replace-cross Abstract: In a world of accelerating change, there is a need for wise and adaptive human reasoning. Integrating AI capabilities with human guidance offers promise, though h…
- arXiv cs.AIresearchVTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
arXiv:2505.13439v2 Announce Type: replace-cross Abstract: Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuou…
- arXiv cs.AIresearchEvaluating the Retrieval Robustness of Large Language Models
arXiv:2505.21870v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG could also lead to perfo…
- arXiv cs.AIresearchRobust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
arXiv:2506.05937v3 Announce Type: replace-cross Abstract: Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimenta…
- arXiv cs.AIresearchMitigating Watermark Forgery in Generative Models via Randomized Key Selection
arXiv:2507.07871v5 Announce Type: replace-cross Abstract: Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be…
- arXiv cs.AIresearchMultimodal Representation Learning Conditioned on Semantic Relations
arXiv:2508.17497v3 Announce Type: replace-cross Abstract: Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text…
- arXiv cs.AIresearchEEGDM: Learning EEG Representation with Latent Diffusion Model
arXiv:2508.20705v5 Announce Type: replace-cross Abstract: Recent advances in self-supervised learning for EEG representation have largely relied on masked reconstruction, where models are trained to recover randomly mask…
- arXiv cs.AIresearchCocoon: A System Architecture for Differentially Private Training with Correlated Noises
arXiv:2510.07304v2 Announce Type: replace-cross Abstract: Machine learning (ML) models memorize and leak training data, causing serious privacy issues to data owners. Training algorithms with differential privacy (DP) ha…
- arXiv cs.AIresearchA Unified BERT-CNN-BiLSTM Framework for Simultaneous Headline Classification and Sentiment Analysis of Bangla News
arXiv:2511.18618v2 Announce Type: replace-cross Abstract: In our daily lives, newspapers are an essential information source that impacts how the public talks about present-day issues. However, effectively navigating the…
- arXiv cs.AIresearchScience Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers
arXiv:2511.21739v2 Announce Type: replace-cross Abstract: We present the first large-scale analysis of AI foundation model usage in science -- not just citations or keywords. We find that adoption has grown rapidly, at n…
- arXiv cs.AIresearchDemystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
arXiv:2512.19905v3 Announce Type: replace-cross Abstract: Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time.…
- arXiv cs.AIresearchMorality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models
arXiv:2512.21439v2 Announce Type: replace-cross Abstract: A key question in current AI alignment research is how to make AI algorithms learn moral values. Because human morality is highly context-dependent, actions are j…
- arXiv cs.AIresearchExtended to Reality: Prompt Injection in 3D Environments
arXiv:2602.07104v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications s…
- arXiv cs.AIresearchANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
arXiv:2602.09009v4 Announce Type: replace-cross Abstract: Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep layers are often under…
- arXiv cs.AIresearchThe Effective Depth Paradox: Topology and Trainability in Deep CNNs
arXiv:2602.13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural fa…
- arXiv cs.AIresearchGoldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
arXiv:2602.14868v3 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this p…
- arXiv cs.AIresearchSensory-Aware Sequential Recommendation via Review-Distilled Representations
arXiv:2603.02709v4 Announce Type: replace-cross Abstract: Sequential recommenders learn behavioral patterns from item identifiers, while the experiential properties that users describe in reviews, such as how products lo…
- arXiv cs.AIresearchEvaluation format, not only model capability, shapes measured triage failure in consumer health AI
arXiv:2603.11413v5 Announce Type: replace-cross Abstract: A recent Nature Medicine study reported that ChatGPT Health under-triages 51.6% of emergencies and concluded that consumer-facing AI triage poses safety risks. It…
- arXiv cs.AIresearchControllable Accent Normalization via Discrete Diffusion
arXiv:2603.14275v3 Announce Type: replace-cross Abstract: Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tun…
- arXiv cs.AIresearchExploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning
arXiv:2603.19307v2 Announce Type: replace-cross Abstract: Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. How…
- arXiv cs.AIresearchSpectral Alignment in Forward-Backward Representations via Temporal Abstraction
arXiv:2603.20103v4 Announce Type: replace-cross Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank fac…
- arXiv cs.AIresearchMany Preferences, Few Policies: Compact Portfolios for Multi-Objective LLM Alignment
arXiv:2604.04144v3 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) requires balancing competing objectives such as helpfulness, harmlessness, and conciseness. The appropriate balance varies a…
- arXiv cs.AIresearchIs a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity
arXiv:2604.04692v3 Announce Type: replace-cross Abstract: Automated fact-checking is a crucial task that supports a responsible information ecosystem. While recent research has progressed from text-only to multimodal fac…
- arXiv cs.AIresearchRhetorical Questions in LLM Representations: A Linear Probing Study
arXiv:2604.14128v3 Announce Type: replace-cross Abstract: Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We a…
- arXiv cs.AIresearchDual Certified White-Box Inference for Input Convex Neural Networks
arXiv:2605.04722v2 Announce Type: replace-cross Abstract: Input convex neural networks (ICNNs) are used to learn convex objectives whose minimizers define decisions, making efficient and reliable optimization central to…
- arXiv cs.AIresearchCoMemNet: A Continual Memory Network with Drift-Aware Sampling for Traffic Prediction
arXiv:2605.05738v2 Announce Type: replace-cross Abstract: Traffic sensor networks evolve as sensors are added and traffic distributions change, whereas most forecasting models assume a fixed node set and repeatedly retra…
- arXiv cs.AIresearchMolWorld: Molecule World Models for Actionable Molecular Optimization
arXiv:2605.08954v2 Announce Type: replace-cross Abstract: Molecular optimization in drug discovery aims to discover molecules with improved target properties, but practical lead optimization often requires more than high…
- arXiv cs.AIresearchDuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis
arXiv:2605.10521v2 Announce Type: replace-cross Abstract: As medical AI expands across diverse healthcare settings worldwide, equitable performance across patient populations is becoming essential to trustworthy clinical…
- arXiv cs.AIresearchMeasuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impact
arXiv:2605.14021v2 Announce Type: replace-cross Abstract: Google AI Overviews (AIOs) are arguably the most widely encountered deployment of generative AI, reaching over 2 billion users who may not realize the answers the…
- arXiv cs.AIresearchLEAF: A Living Benchmark for Event-Augmented Forecasting
arXiv:2605.16358v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly applied to real-world forecasting tasks, yet evaluating their true predictive capability remains compromised by pre-…