AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchOpen Benchmark of AI Impact on Humans (ImpactBench): an expert-guided, open platform for the holistic evaluation of AI impact on humans
arXiv:2610.20690v1 Announce Type: cross Abstract: The present work is concerned with how to measure, at scale, the multi-dimensional impact of generative AI models on the individuals who use them. In service of this goal…
- arXiv cs.AIresearchWorldCast: Exploring Intelligent Visual Generation in World State Prediction
arXiv:2610.20731v2 Announce Type: replace-cross Abstract: Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities…
- arXiv cs.AIresearchInterpreting Language Model Parameters
arXiv:2610.20748v1 Announce Type: cross Abstract: Mechanistic interpretability aims to uncover how neural networks use their parameters to implement their impressive neural algorithms. Although previous work has uncovere…
- arXiv cs.AIresearchOptimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets
arXiv:2610.20753v1 Announce Type: cross Abstract: Large language models (LLMs) trained on vast amounts of data have demonstrated impressive performance over a range of tasks, but future performance gains will require inc…
- arXiv cs.AIresearchReference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models
arXiv:2610.20763v1 Announce Type: cross Abstract: Full-duplex spoken language models decide at every frame whether to take the floor, defining a conversational personality -- yet each set of weights encodes exactly one,…
- arXiv cs.AIresearchVerdict: Encode Once, Decide Many
arXiv:2610.20778v1 Announce Type: cross Abstract: Automating organizational work means answering many small typed questions about one piece of state (does this email need a reply, how urgent is it, who owns it) with prob…
- arXiv cs.AIresearchReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
arXiv:2610.20781v1 Announce Type: cross Abstract: Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training couples these tasks,…
- arXiv cs.AIresearchWolof-Adapted Industry-Ready Open-Weight Language Models
arXiv:2610.20824v1 Announce Type: cross Abstract: Wolof is spoken by 23M people, mostly in Senegal, but remains weakly supported by open-weight language models, while API models raise cost, governance, and sovereignty co…
- arXiv cs.AIresearchCoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
arXiv:2610.20828v1 Announce Type: cross Abstract: Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT generation (FCG) fo…
- arXiv cs.AIresearchAmortizing Sequential Experimental Design in Reasoning LLMs
arXiv:2610.20832v1 Announce Type: cross Abstract: Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental de…
- arXiv cs.AIresearchProbing Negation Understanding in Vision-Language Models With Object Attention
arXiv:2610.20852v1 Announce Type: cross Abstract: Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively. We investigate how VLMs p…
- arXiv cs.AIresearchWrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
arXiv:2610.20898v1 Announce Type: cross Abstract: Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards.…
- arXiv cs.AIresearchTGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping
arXiv:2610.20901v1 Announce Type: cross Abstract: Task-Oriented Grasping (TOG) has emerged as an important skill for purposeful robotic manipulation. Given the task of using a knife to "slice bread," a robot must choose…
- arXiv cs.AIresearchReplicable Dueling Bandits
arXiv:2610.20908v1 Announce Type: cross Abstract: Dueling bandits choose each comparison based on earlier noisy outcomes, so two runs on the same preferences can compare different pairs. We study replicable dueling bandi…
- arXiv cs.AIresearchForecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models
arXiv:2610.20918v1 Announce Type: cross Abstract: Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts. We examined how fo…
- arXiv cs.AIresearchSOMA: Stack-of-Objects Manipulation using a Quadruped Robot
arXiv:2610.20968v1 Announce Type: cross Abstract: Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulators. This paper prese…
- arXiv cs.AIresearchHow to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts
arXiv:2610.20980v1 Announce Type: cross Abstract: Compiler transformations interact, making GPU kernel optimization a search for combinations that preserve the computation while improving performance. We introduce HOW TO…
- arXiv cs.AIresearchEigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation?
arXiv:2610.20999v1 Announce Type: cross Abstract: Diffusion models are notoriously expensive to train, requiring large-scale datasets to learn how to gradually reverse the noise from images over multiple small denoising…
- arXiv cs.AIresearchLearning to Read Out: Unembedding Dynamics in Language Model Pretraining
arXiv:2610.21025v1 Announce Type: cross Abstract: When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction…
- arXiv cs.AIresearchPremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews
arXiv:2610.21046v1 Announce Type: cross Abstract: Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce ReviewFact, a benchma…
- arXiv cs.AIresearchBellman-Consistent Trajectory RL for LLM Arithmetic Reasoning
arXiv:2610.21060v1 Announce Type: cross Abstract: To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method. Our framework introduces Trajectory Bellman Residual…
- arXiv cs.AIresearchA Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models
arXiv:2610.21085v2 Announce Type: replace-cross Abstract: An ensemble of language models is a jury, not an electorate. The answers are testimony from witnesses of unknown reliability, and the question is not what the maj…
- arXiv cs.AIresearchSIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
arXiv:2610.21087v1 Announce Type: cross Abstract: We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological…
- arXiv cs.AIresearchDST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting
arXiv:2610.21123v1 Announce Type: cross Abstract: Series decomposition has emerged as a widely acknowledged paradigm in deep time series forecasting models. However, existing approaches predominantly employ a homogeneous…
- arXiv cs.AIresearchWhen Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation
arXiv:2610.21128v1 Announce Type: cross Abstract: Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that…
- arXiv cs.AIresearchOnBodyAI - Why the Next AI Needs a Body
arXiv:2610.21137v1 Announce Type: cross Abstract: The next AI will not win by knowing more about the world. It will win because it knows you: because it lives on your body, works for you and answers to you. That is what…
- arXiv cs.AIresearchWhen is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles
arXiv:2610.21139v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used upstream of decision-making to clean data, detect label errors, and reconstruct missing values. Yet LLM-assisted data c…
- arXiv cs.AIresearchCoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
arXiv:2610.21143v1 Announce Type: cross Abstract: Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate…
- arXiv cs.AIresearchCARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequent…
- arXiv cs.AIresearchLanguage Models Share a Readout Bottleneck in Working Memory
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and errors concentrate on lur…
- arXiv cs.AIresearchJudging the Judges: Confidence and Disagreement in Rubrics as Rewards
arXiv:2610.21179v1 Announce Type: cross Abstract: Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric. Prior work has foc…
- arXiv cs.AIresearchFedPix: Learning What to Share with Less Leakage in Federated Intelligence
arXiv:2610.21194v2 Announce Type: replace-cross Abstract: Existing federated intelligence paradigms primarily focus on how models are trained or aggregated, while overlooking a more fundamental question: \textbf{what inf…
- arXiv cs.AIresearchRecSoup: Efficient Model Merging Approach for Controllable Multi-Objective Recommendation
arXiv:2610.21220v1 Announce Type: cross Abstract: Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective Recommendation (CMOR) enables dynamic adjustment of objective trad…
- arXiv cs.AIresearchRepresentation Redistribution in Sparse Autoencoders
arXiv:2610.21240v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying request can redistrib…
- arXiv cs.AIresearchSystem1-Arena: Which Decisions Can Be Left to System 1?
arXiv:2610.21244v1 Announce Type: cross Abstract: Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the OpenAI Decisions API,…
- arXiv cs.AIresearchWhat do AI chatbots do after users decline therapeutic redirection for suicide thoughts?
arXiv:2610.21253v1 Announce Type: cross Abstract: Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements urging users who disclose suicide thoughts to seek help from cris…
- arXiv cs.AIresearchFractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference
arXiv:2610.21257v1 Announce Type: cross Abstract: Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and energy cost. Post-train…
- arXiv cs.AIresearchBehavioral Compositionality of Sparse Autoencoder Representations
arXiv:2610.21261v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) represent model activations with sparse, linearly decoded features, but the downstream effects of those features need not compose additively. W…
- arXiv cs.AIresearchTRACER: A Multimodal Harness for Patient Care in Hospitals
arXiv:2610.21266v1 Announce Type: cross Abstract: Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central challenge is how to…
- arXiv cs.AIresearchLoud and Clear: Making Visual Evidence Count in Multimodal Document RAG
arXiv:2610.21318v1 Announce Type: cross Abstract: Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model reads the retrieved…
- arXiv cs.AIresearchDoes On-Policy Distillation Need to Complete Every Rollout?
arXiv:2610.21337v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) transfers teacher knowledge to a student through feedback on student-generated rollouts, but generating complete rollouts and computi…
- arXiv cs.AIresearchLTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models
arXiv:2610.21362v1 Announce Type: cross Abstract: Robotic manipulation often requires remembering interactions that are no longer visible. We introduce Latent Transition Memory (LTM), which stores history as compact late…
- arXiv cs.AIresearchESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases
arXiv:2610.21368v1 Announce Type: cross Abstract: With the expansion of pre-trained language model usage in recent years, the importance of datasets for performing tasks in specialized domains has significantly increased…
- arXiv cs.AIresearchWhen do quantum views help? Complementary classical-quantum representations in multi-view fusion
arXiv:2610.21395v1 Announce Type: cross Abstract: Recent studies have reported promising results from quantum machine learning in drug discovery, healthcare, materials science and cybersecurity. Research includes compari…
- arXiv cs.AIresearchMulti-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense
arXiv:2610.21404v1 Announce Type: cross Abstract: To improve task performance while encouraging desirable response properties, LLM post-training often combines a primary reward (e.g., correctness) with auxiliary rewards…
- arXiv cs.AIresearchWhere, How, and When: Query-Guided Grounding for Video Understanding
arXiv:2610.21422v1 Announce Type: cross Abstract: Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and localizing when specific…
- arXiv cs.AIresearchV-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms
arXiv:2610.21448v1 Announce Type: cross Abstract: In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the action-value function i…
- arXiv cs.AIresearchFull-Duplex Interaction with Speech, Expressions and Gestures
arXiv:2610.21452v1 Announce Type: cross Abstract: Human face-to-face conversation requires coordinating speech, gestures and expressions across both speaking and listening. We present ELLSA 2, an end-to-end full-duplex d…
- arXiv cs.AIresearchCan Visual Generation Expand What Unified Multimodal Models Know?
arXiv:2610.21459v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learning to generate image…
- arXiv cs.AIresearchCan LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation
arXiv:2610.21468v1 Announce Type: cross Abstract: Every story has two orders: the order in which its events happen and the order in which they are told. A story is nonlinear when the two differ. We introduce a benchmark…