AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDNAlign: Dynamic Null-Space Safe Alignment for LLMs
arXiv:2610.02844v1 Announce Type: new Abstract: Ensuring the safe and reliable deployment of large language models (LLMs) remains a fundamental challenge. Existing safety alignment approaches either incur high computatio…
- arXiv cs.AIresearchBounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection performance has bee…
- arXiv cs.AIresearchTACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control
arXiv:2610.02867v1 Announce Type: new Abstract: Recent text-to-motion models have improved motion quality and instruction following, yet many-step denoising and large model components make deployment slow and memory-inte…
- arXiv cs.AIresearchLUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
arXiv:2610.02902v3 Announce Type: replace Abstract: Current analyses of LLMs' parametric knowledge are largely output-centric, drawing conclusions about what a model knows without verifying what it was actually trained o…
- arXiv cs.AIresearchFrequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM
arXiv:2610.02910v1 Announce Type: new Abstract: Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which experts to suppress i…
- arXiv cs.AIresearchReasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation
arXiv:2610.02968v1 Announce Type: new Abstract: Large language models (LLMs) can infer user preferences from interaction histories and reviews, yet the rationales they generate may not reflect the information actually us…
- arXiv cs.AIresearchCreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening
arXiv:2610.02972v1 Announce Type: new Abstract: Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability model to every candidate and criterion is costly. We present CreateSc…
- arXiv cs.AIresearchReliable Self-Evolution with Imperfect Proxy Rewards
arXiv:2610.02975v1 Announce Type: new Abstract: Large language model (LLM)-based self-evolving search is a promising approach to scientific discovery. However, high-fidelity evaluation of every candidate is prohibitively…
- arXiv cs.AIresearchRelevant Evidence Decoding for Audio-Visual Hallucination Mitigation
arXiv:2610.02976v1 Announce Type: new Abstract: Audio-Visual Large Language Models (AV-LLMs) remain prone to cross-modal hallucinations, where one modality incorrectly affects predictions about another. Although contrast…
- arXiv cs.AIresearchRASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction
arXiv:2610.02979v1 Announce Type: new Abstract: Unstructured discharge notes in Electronic Health Records (EHRs) often carry signal complementary to structured medical codes, holding patient-specific evidence that standa…
- arXiv cs.AIresearchSafeguarding Mutual Correction in Source-Free Domain Adaptation via Cut Statistics
arXiv:2610.02981v1 Announce Type: new Abstract: Source-Free Domain Adaptation (SFDA) aims to adapt a source-pretrained model to an unlabeled target domain without access to the original source domain. While early single-…
- arXiv cs.AIresearchPLCWorld: Benchmarking LLM-Generated PLC Programs in Closed-Loop Plant Simulation
arXiv:2610.02982v1 Announce Type: new Abstract: Programmable logic controllers (PLCs) coordinate industrial equipment by reading sensor inputs and issuing control commands. Evaluating whether large language model (LLM)-g…
- arXiv cs.AIresearchPersonalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations
arXiv:2610.03017v1 Announce Type: new Abstract: This work presents an automatic speech recognition (ASR) system personalized for a Czech speaker with a permanent tracheal stoma and severe dysarthria rendering their speec…
- arXiv cs.AIresearchVerifiable, Articulable, and Tacit Components of Preference
arXiv:2610.03025v2 Announce Type: replace Abstract: What makes a short story gripping; a news article newsworthy; or a math proof elegant? These constructs resist articulation or verification; their meaning is at least p…
- arXiv cs.AIresearchSoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set Annotation
arXiv:2610.03029v1 Announce Type: new Abstract: Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological interpretation. Whi…
- arXiv cs.AIresearchRIFAR: Reliability-Informed and Forgetting-Aware Replay for Continual Robot Learning with World-Action Models
arXiv:2610.03079v3 Announce Type: replace Abstract: Genuine embodied agency requires robots to turn continuous real-world experience into lasting, transferable skills. This demands continual learning that integrates new…
- arXiv cs.AIresearchPredictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression
arXiv:2610.03098v2 Announce Type: replace Abstract: Codon optimization, the process of selecting synonymous codons to improve mRNA translation efficiency and protein expression, is central to therapeutic protein producti…
- arXiv cs.AIresearchTrading Strategy Optimization via Textual Gradient
arXiv:2610.03128v2 Announce Type: replace Abstract: Quantitative trading strategy design aims to discover trading programs from historical data that remain effective in future markets, which can be viewed as a black-box…
- arXiv cs.AIresearchKeeping JEPA World Models Plannable When Little of the Frame Moves
arXiv:2610.03137v1 Announce Type: new Abstract: Specifying a goal in language rather than as a goal frame is a natural interface for planning with a latent world model, but testing it needs scenes in which language must…
- arXiv cs.AIresearchGains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
arXiv:2610.03185v1 Announce Type: new Abstract: On-policy distillation (OPD) has become an important approach to language model post-training. However, despite its performance gains, OPD can also collapse into excessivel…
- arXiv cs.AIresearchKV$^2$: A Self-Refining KV Cache
arXiv:2610.03198v2 Announce Type: replace Abstract: The memory footprint of the key-value (KV) cache constrains the practical use of long-context models, and it dominates cost when one prefilled context must later serve…
- arXiv cs.AIresearchLearning a Fact Is Not Learning How to Retrieve It
arXiv:2610.03251v2 Announce Type: replace Abstract: A model trained on "The capital of X is Y" may produce "Y" after "The capital of X is" but fail after "The capital of X:." We call these different ways of eliciting the…
- arXiv cs.AIresearchEVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation
arXiv:2610.03273v1 Announce Type: new Abstract: Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concepts without intermedia…
- arXiv cs.AIresearchJOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
arXiv:2610.03296v1 Announce Type: new Abstract: Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parallelism and enabling s…
- arXiv cs.AIresearchOptimal Planning in a Dynamic World
arXiv:2610.03312v1 Announce Type: new Abstract: Background: We address the problem of planning when the set of feasible states or actions changes over time. For example, in the problem of path planning among moving obsta…
- arXiv cs.AIresearchMulti-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs
arXiv:2610.03316v2 Announce Type: replace Abstract: Designing effective heuristics for diverse combinatorial optimization problems requires substantial expertise and repeated search. Large language models (LLMs) automate…
- arXiv cs.AIresearchRefinement Buys Intelligibility, Search Buys Identity: What Test-Time Compute Buys in Masked-Diffusion TTS
arXiv:2610.03320v1 Announce Type: new Abstract: Diffusion language models for text-to-speech combine two forms of computation: model depth (parameters) and refinement steps (inference budget). We ask whether they scale e…
- arXiv cs.AIresearchPreserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation
arXiv:2610.03326v1 Announce Type: new Abstract: Diffusion language model (dLLM) compression faces a known challenge because calibration is typically performed on clean, fully visible activations, whereas inference traver…
- arXiv cs.AIresearchGeometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers
arXiv:2610.03363v3 Announce Type: replace Abstract: Neural surrogate models for Partial Differential Equations (PDEs) on unstructured 3D geometries are often limited by poor generalization and the high cost of generating…
- arXiv cs.AIresearchMultilingual GSM-Symbolic: What determines capability transfer across languages?
arXiv:2610.03367v2 Announce Type: replace Abstract: We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incomparable, saturation-…
- arXiv cs.AIresearchCVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models
arXiv:2610.03383v1 Announce Type: new Abstract: Attack Path (AP) modeling is fundamental to cybersecurity analysis, where the Planning Domain Definition Language (PDDL) has been widely adopted to encode APs into formal a…
- arXiv cs.AIresearchBenchmarking candidate coverage and rejection policy transfer in typed decision models
arXiv:2610.03387v2 Announce Type: replace Abstract: Rejection policies must remain useful as candidate sets and tasks change. We compare Laya, Jev and Qwen2.5-7B-Instruct using public reference labels, testing Laya/Jev p…
- arXiv cs.AIresearchBecoming Suspicious Across Borders: Algorithmic Extraterritoriality and AI-Driven Financial Surveillance
arXiv:2610.03425v1 Announce Type: new Abstract: Suspicion is an important, yet elusive concept in anti-money laundering and counter-terrorist financing (AML/CFT), which allows for intervention below the threshold of proo…
- arXiv cs.AIresearchJumping the Line: Exploiting Length Predictions in LLM Scheduling
arXiv:2610.03430v1 Announce Type: new Abstract: Efficient request scheduling is increasingly important for reducing completion time in large language model (LLM) serving. Size-based policies such as Shortest Job First pr…
- arXiv cs.AIresearchA Near-Zero Monitor Readout Is Not Evidence of Behavioral Control
arXiv:2610.03458v1 Announce Type: new Abstract: Post-training with verifiable rewards can induce reward hacking, motivating the use of monitors within the training objective rather than solely for offline auditing. We sh…
- arXiv cs.AIresearchEfficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
arXiv:2610.03509v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning allows humans to inspect how large language models reach their answers, and oversee model behaviour. This reasoning comes at an increased i…
- arXiv cs.AIresearchReasoning Models Are Accurate but Unsound on Identification
arXiv:2610.03519v1 Announce Type: new Abstract: A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers a nonidentifiable o…
- arXiv cs.AIresearchFrom Benchmarks to Production: A Text-to-SQL System for Complex Financial Data
arXiv:2610.03524v1 Announce Type: new Abstract: General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often…
- arXiv cs.AIresearchRecursive Harness Self-Improvement for Frontier Reasoning Data Synthesis
arXiv:2610.03548v1 Announce Type: new Abstract: Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated…
- arXiv cs.AIresearchLearning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing
arXiv:2610.03570v1 Announce Type: new Abstract: Contactless heart-rate sensing with millimeter-wave (mmWave) radar requires assessing whether individual measurements support reliable estimation. We study learning to asse…
- arXiv cs.AIresearchVideo-Time Priors for EEG-fNIRS Emotion Regression on Familiar Videos
arXiv:2610.03618v2 Announce Type: replace Abstract: Do viewer-specific physiological signals improve continuous emotion regression beyond the stimulus-driven response shared across viewers? We examine this question by pr…
- arXiv cs.AIresearchDepth as Time in One-Step Generative Models
arXiv:2610.03626v1 Announce Type: new Abstract: The recent wave of one-step generative models, which compress the multi-step trajectory of diffusion via either distillation or learned flow maps, has reached an inflection…
- arXiv cs.AIresearchDo Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
arXiv:2610.03639v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support legal practice, education, and research, yet their reliability in national legal systems outside the United St…
- arXiv cs.AIresearchMRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
arXiv:2610.03651v1 Announce Type: new Abstract: Dense-retrieval services must switch among embedding-prefix dimensions and index bit rates as latency, quality, and memory budgets change. Tuning a quantizer separately for…
- arXiv cs.AIresearchTranscriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies
arXiv:2610.03693v1 Announce Type: new Abstract: Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoa…
- arXiv cs.AIresearchIntentCoding: Amplifying User Intent in Code Generation
arXiv:2602.00066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a signif…
- arXiv cs.AIresearchMulti-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework
arXiv:2606.26567v1 Announce Type: cross Abstract: High-frequency massive multiple-input multiple-output (MIMO) systems promise ultra-high data rates. However, efficient beam management remains challenging due to the proh…
- arXiv cs.AIresearchGlanceWAM: Sparse Test-Time Imagination for World-Action Models
arXiv:2608.23927v3 Announce Type: replace-cross Abstract: Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchronous video g…
- arXiv cs.AIresearchCausal discovery identifies pathways linking physical activity to dementia risk in the UK BioBank
arXiv:2610.02221v1 Announce Type: cross Abstract: Physical Activity (PA) is consistently associated with lower risk of dementia, yet the mechanism linking PA to dementia prevention remain incomopletely understood. Here,…
- arXiv cs.AIresearchOne Distribution, Two Channels: Coverage-Calibrated KV Retention and Compensation
arXiv:2610.02235v2 Announce Type: replace-cross Abstract: Long-context decoding is increasingly constrained by key--value (KV) cache memory and bandwidth. Existing fixed-budget compression methods typically separate rete…