AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSLEM: Spectrum-Aware Latent Expert Merging
arXiv:2610.16484v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all parameters to be s…
- arXiv cs.AIresearchGrowing and Transferring Pathways for LLM Reinforcement Learning
arXiv:2610.16489v1 Announce Type: cross Abstract: Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources.…
- arXiv cs.AIresearchpi-Net: Empirical Latent Representations for Differentiable Physics Heads in Data-Scarce Systems
arXiv:2610.16504v1 Announce Type: cross Abstract: Developing reliable predictive models for multi-physics systems often forces a compromise between computationally demanding physical simulators and data-hungry, opaque ma…
- arXiv cs.AIresearchPatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation evaluation
arXiv:2610.16538v1 Announce Type: cross Abstract: We present PatTransBench, a 12,000-item Chinese-English/Japanese/Korean patent machine translation (PatMT) benchmark with a four-dimensional evaluation protocol. The benc…
- arXiv cs.AIresearchHeuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration
arXiv:2610.16545v1 Announce Type: cross Abstract: Feature caching has become a mainstream training-free strategy for accelerating video diffusion models by reusing intermediate outputs across denoising steps. However, ex…
- arXiv cs.AIresearchVLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models
arXiv:2610.16567v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) have achieved high success rates on familiar manipulation tasks, yet it remains unclear whether such scores reflect genuine zero-shot…
- arXiv cs.AIresearchTowards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals
arXiv:2610.16596v2 Announce Type: replace-cross Abstract: Seizure prediction and detection, essential for clinical treatment of epilepsy, remain the crucial task of this neurological disease. EEG and iEEG are widely used…
- arXiv cs.AIresearchMixLID: Token-Level Language Identification in Mixed-Language Text
arXiv:2610.16601v1 Announce Type: cross Abstract: Processing multilingual text requires both identifying a broad range of languages and distinguishing the language of each token in inputs containing multiple languages. W…
- arXiv cs.AIresearchAnswer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models
arXiv:2610.16622v1 Announce Type: cross Abstract: With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs). Despite the new, t…
- arXiv cs.AIresearchIntegrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
arXiv:2610.16627v1 Announce Type: cross Abstract: Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving…
- arXiv cs.AIresearchAeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting--Extended Version
arXiv:2610.16630v1 Announce Type: cross Abstract: Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary p…
- arXiv cs.AIresearchREEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
arXiv:2610.16632v1 Announce Type: cross Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner,…
- arXiv cs.AIresearchSuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba
arXiv:2610.16636v1 Announce Type: cross Abstract: State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grows. We propose SuPER-…
- arXiv cs.AIresearchLearning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting
arXiv:2610.16645v1 Announce Type: cross Abstract: Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to…
- arXiv cs.AIresearchFeature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
arXiv:2610.16694v1 Announce Type: cross Abstract: Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erodes any trained deci…
- arXiv cs.AIresearchVAttnPO: Visual Attention-Guided Policy Optimization
arXiv:2610.16735v1 Announce Type: cross Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal distinguishes overall r…
- arXiv cs.AIresearchBefore Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation
arXiv:2610.16745v1 Announce Type: cross Abstract: Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing that geometry alters w…
- arXiv cs.AIresearchRelational Learning as World Modeling
arXiv:2610.16763v1 Announce Type: cross Abstract: Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action? In operational sy…
- arXiv cs.AIresearchInfoVis: Unified Slide Image Generation and Editing
arXiv:2610.16784v1 Announce Type: cross Abstract: Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise edit…
- arXiv cs.AIresearchLogit Leakage through Floating-Point Bias Addition
arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relative logits, leaving a…
- arXiv cs.AIresearchStableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recom…
- arXiv cs.AIresearchGrowing to See: Efficient Pretraining of Self-Supervised Vision Transformers
arXiv:2610.16817v1 Announce Type: cross Abstract: Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language models have renewed…
- arXiv cs.AIresearchDTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
arXiv:2610.16822v1 Announce Type: cross Abstract: Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. The key diffic…
- arXiv cs.AIresearchUnsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
arXiv:2610.16826v1 Announce Type: cross Abstract: Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording c…
- arXiv cs.AIresearchA Scaled-Up Empirical Study of Syntactic Language Models
arXiv:2610.16837v1 Announce Type: cross Abstract: Syntactic language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalization and downstream tas…
- arXiv cs.AIresearchFew-for-Many Best-Arm Identification in Multi-Objective Bandits
arXiv:2610.16840v1 Announce Type: cross Abstract: Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in…
- arXiv cs.AIresearchTowards Cost-Efficient Video Dataset Construction with Large Language Models
arXiv:2610.16857v1 Announce Type: cross Abstract: Research on video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for datasets to train such models.…
- arXiv cs.AIresearchComparing GenAI to Machine Learning and Manual Review for eDiscovery
arXiv:2610.16925v3 Announce Type: replace-cross Abstract: Keeling et al. [Keeling2026Generative] report on a case study recently conducted by Redgrave LLP in which they assert that Relativity's Generative AI Review tool…
- arXiv cs.AIresearchKNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
arXiv:2610.16940v1 Announce Type: cross Abstract: Nearest neighbor search algorithms are widely used and have a long history, but we find that key implementation details are seldom reviewed in articles about them. These…
- arXiv cs.AIresearchUA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition
arXiv:2610.16942v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized domains remains largely o…
- arXiv cs.AIresearchSocial Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate
arXiv:2610.16946v1 Announce Type: cross Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users changes how it treats pe…
- arXiv cs.AIresearchSarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection
arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly hateful wording. Sa…
- arXiv cs.AIresearchProactive Physical AI through Continuous Observation and Timely Intervention
arXiv:2610.16967v1 Announce Type: cross Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real-world settings, h…
- arXiv cs.AIresearchThe Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
arXiv:2610.16977v1 Announce Type: cross Abstract: Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends critically on the e…
- arXiv cs.AIresearchWeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment
arXiv:2610.16979v3 Announce Type: replace-cross Abstract: Generative retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework. However, effectiv…
- arXiv cs.AIresearchFrom Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning
arXiv:2610.16984v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn effective policies from fixed datasets without environment interaction. Although generative models such as diffusion and flow…
- arXiv cs.AIresearchTabGift: A Context-Efficient Foundation Model for Tabular Data Generation
arXiv:2610.16990v1 Announce Type: cross Abstract: Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabular foundation mod…
- arXiv cs.AIresearchGoverning Copyright Responsibly in the Era of Generative AI
arXiv:2610.17002v1 Announce Type: cross Abstract: Large language models are trained on collections that may include scholarly works, while authors generally lack work-level information about whether and how their works w…
- arXiv cs.AIresearchMAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
arXiv:2610.17014v2 Announce Type: replace-cross Abstract: Functional brain connectome represents neural connectivity as a matrix of pairwise interactions between brain regions. Generation of functional connectomes is not…
- arXiv cs.AIresearchProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
arXiv:2610.17016v1 Announce Type: cross Abstract: Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities u…
- arXiv cs.AIresearchSPLICE: Sparse Physics Library Identification and Compositional Expansion
arXiv:2610.17029v1 Announce Type: cross Abstract: Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing approaches, however, re…
- arXiv cs.AIresearchGradient Routing Localizes and Removes Unintended Behaviors in RL
arXiv:2610.17062v1 Announce Type: cross Abstract: We propose a mitigation to reward hacking in reinforcement learning. Our setup involves a misspecified reward function that gives rise to unintended behavior, and a monit…
- arXiv cs.AIresearchSuperintelligence and the Triple Risk of an AI Race
arXiv:2610.17085v1 Announce Type: cross Abstract: On many estimates, artificial general intelligence (AGI) is likely to emerge within the next few decades or even sooner. Once it does, it may quickly surpass human intell…
- arXiv cs.AIresearchWhat the Machine Invented: Mining New Mathematical Instruments from OpenAI's October 2026 Release of AI-Generated Mathematics
arXiv:2610.17090v1 Announce Type: cross Abstract: On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository github.com/openai/mat…
- arXiv cs.AIresearchAIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages
arXiv:2610.17110v1 Announce Type: cross Abstract: AI-assisted research leaves instructions, computations, artifact revisions and checks whose relationships matter when another researcher receives the work. We present AIP…
- arXiv cs.AIresearchCalibrated Typed Decisions for Entity, Relation, and Event Extraction
arXiv:2610.17113v1 Announce Type: cross Abstract: Information extraction models often perform well on the datasets they are trained on, but transferring to new domains and annotation guidelines remains challenging. Suppo…
- arXiv cs.AIresearchD-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control
arXiv:2610.17114v1 Announce Type: cross Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, held in network weigh…
- arXiv cs.AIresearchD2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones
arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-SLMs) in general cap…
- arXiv cs.AIresearchSonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning
arXiv:2610.17131v3 Announce Type: replace-cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried ti…
- arXiv cs.AIresearchForce-Modulated Dexterity: Unified Compliance for Contact-Rich Manipulation
arXiv:2610.17161v1 Announce Type: cross Abstract: Teleoperation is widely used to collect high-quality demonstrations for robot learning. Dexterous manipulation, however, requires coordinated control of motion and contac…