AI news archive.
19,854 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchThe Router Already Knows
arXiv:2610.27421v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models already make a sparse choice for every token: which experts should process it. We ask whether a sparse dictionary should reuse that choice…
- arXiv cs.AIresearchMLIPS: Multi-Layer Indexer Pool Sharing
arXiv:2610.27438v2 Announce Type: replace-cross Abstract: Sparse attention limits the keys used by each query, but finding those keys can still require a full-prefix scan at every layer. We introduce $MLIPS:$ $Multi$-$La…
- arXiv cs.AIresearchScaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings
arXiv:2610.27439v1 Announce Type: cross Abstract: Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph. This approach result…
- arXiv cs.AIresearchBeyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM Arenas
arXiv:2610.27447v1 Announce Type: cross Abstract: The evaluation of large language models (LLMs) is inherently multi-objective, as different models may offer different tradeoffs across performance dimensions such as math…
- arXiv cs.AIresearchProjected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets
arXiv:2610.27467v1 Announce Type: cross Abstract: On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilities. On hard problems…
- arXiv cs.AIresearchTraining-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
arXiv:2610.27468v1 Announce Type: cross Abstract: Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be…
- arXiv cs.AIresearchPrivacy-Preserving Personalized Federated Learning (PPP-FL) for Medical Imaging
arXiv:2610.27470v1 Announce Type: cross Abstract: Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-border data sharing restrictions, and enhances privacy…
- arXiv cs.AIresearchBeyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
arXiv:2610.27473v1 Announce Type: cross Abstract: Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such associations can be implanted so that ordinary prompts…
- arXiv cs.AIresearchOrthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models
arXiv:2610.27490v1 Announce Type: cross Abstract: Mitigating catastrophic risks from large language models requires excising hazardous operational capabilities, such as cyberwarfare exploitation and pathogen enhancement,…
- arXiv cs.AIagentsSelf-Evolving Agents through Privileged Retrospective Distillation
arXiv:2610.27495v1 Announce Type: cross Abstract: Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solu…
- arXiv cs.AIresearchCross-Visibility-Gap Identity Persistence for 4D Scene Graphs
arXiv:2610.27505v1 Announce Type: cross Abstract: 4D scene graphs require persistent object identity when an object disappears inside an opaque carrier and later reappears as a fresh detection. When appearance and target…
- arXiv cs.AIresearchProgressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation
arXiv:2610.27515v1 Announce Type: cross Abstract: Pretrained Vision-Language Models (PVLMs) achieve strong zero-shot recognition but often suffer performance degradation under target-domain shift. Unsupervised adaptation…
- arXiv cs.AIresearchHealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image Generation
arXiv:2610.27516v1 Announce Type: cross Abstract: Despite advances in photorealism, semantic fidelity, and aesthetics, text-to-image generation and image editing remain understudied in a human-centered dimension: whether…
- arXiv cs.AIresearchAdversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
arXiv:2610.27533v1 Announce Type: cross Abstract: Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended to improve benchmark scores. We introduce BenchDoo…
- arXiv cs.AIresearchLess is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval
arXiv:2610.27538v1 Announce Type: cross Abstract: Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image based on a reference image and modification text. Recent approaches commonly rely on large vis…
- arXiv cs.AIresearchCan Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy Distillation
arXiv:2610.27555v1 Announce Type: cross Abstract: Safety pretraining has emerged as a promising paradigm for embedding safety deeply into a model during pretraining, yielding robustness to subsequent fine-tuning that con…
- arXiv cs.AIresearchAnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks
arXiv:2610.27558v1 Announce Type: cross Abstract: Memory-based temporal graph neural networks (TGN) rely on recurrent node memories to capture evolving interaction histories. However, temporal mini-batching introduces a…
- arXiv cs.AIresearchCityPaint: A Free Lunch from 2D Diffusion for City-Scale 3D Texturing
arXiv:2610.27564v1 Announce Type: cross Abstract: Generating high-fidelity, city-scale 3D environments plays a crucial role in applications such as virtual reality, gaming, and urban digital twins. However, the scarcity…
- arXiv cs.AIresearchAnomalyJev: Towards Evaluating Image Anomaly Explanations via Claim-Level Verification
arXiv:2610.27565v1 Announce Type: cross Abstract: Recent multimodal LLM (MLLM)-based anomaly detection (AD) methods can generate textual explanations that help interpret their predictions. However, reliably and efficient…
- arXiv cs.AIresearchLearned Readout Tokens for Extracting Large Language Model Confidence
arXiv:2610.27566v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used within everyday applications where their responses have significant downstream impacts. For responsible deployment of s…
- arXiv cs.AIresearchAudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment
arXiv:2610.27567v1 Announce Type: cross Abstract: Depression assessment from counseling speech requires integrating textual and acoustic psychological evidence across turns, yet existing end-to-end classification approac…
- arXiv cs.AIresearchTRCM: Topology-Aware Route-Consistency Modeling for Robust Neural Vehicle Routing
arXiv:2610.27568v1 Announce Type: cross Abstract: Neural combinatorial optimization has enabled fast constructive solvers for the Capacitated Vehicle Routing Problem (CVRP), yet most autoregressive models still construct…
- arXiv cs.AIresearchFactual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval
arXiv:2610.27580v1 Announce Type: cross Abstract: Factual recall is a lookup: some representation inside the network serves as the key, and what that key is made of decides which queries can retrieve the fact, what an ed…
- arXiv cs.AIresearchBenefit and Cost of Random-Token Replacement under Repeated Data: A Known-Entropy Decomposition and Evidence from Ten Real Corpora
arXiv:2610.27590v1 Announce Type: cross Abstract: When unique pretraining data is scarce, models see the same tokens many times and are thought to memorize. Random-token replacement, an input-corruption augmentation, is…
- arXiv cs.AIagentsWORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot
arXiv:2610.27597v1 Announce Type: cross Abstract: Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely examining concurrently how models discover evidence aut…
- arXiv cs.AIagentsAuditing the Product, Not the Recursion: The Evaluation Evidence Behind Recursive Self-Improvement Claims
arXiv:2610.27610v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) promises AI systems, such as self-evolving LLM agents, that become better at producing further improvements. Evaluating this promise requ…
- arXiv cs.AIresearchABench: Adversarily Benchmarking Large Language Models across Taxonomized Values
arXiv:2610.27611v1 Announce Type: cross Abstract: Ensuring the alignment of Large Language Models (LLMs) with diverse cultural values is critical for their safe global deployment. However, existing alignment benchmarks a…
- arXiv cs.AIresearchLearning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical Systems
arXiv:2610.27614v1 Announce Type: cross Abstract: Complex chemical systems containing heterogeneous substructures are common in real-world applications. Various physical phenomena of the complex chemical systems are deri…
- arXiv cs.AIagentsLocal Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compo…
- arXiv cs.AIresearchA Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving Camera
arXiv:2610.27622v1 Announce Type: cross Abstract: Handheld demonstration devices decouple data collection from the robot, but conventional designs burden the hand with a wrist camera, cables and a pose tracker (SLAM, an…
- arXiv cs.AIresearchBCT: Bayes-Consistent Tempering for Flow Language Models
arXiv:2610.27641v1 Announce Type: cross Abstract: Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates two mismatches. Firs…
- arXiv cs.AIresearchCorpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline
arXiv:2610.27652v1 Announce Type: cross Abstract: Practitioners building training corpora with a pipeline of language models keep a preprocessing or refinement (post-process) stage when switching it on raises the corpus…
- arXiv cs.AIresearchA Unified Attack Framework against Statistical Generative Watermarks for Large Language Models
arXiv:2610.27653v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the…
- arXiv cs.AIresearchPairwise Learning Increases Data Efficiency in Deep Neural Networks
arXiv:2610.27669v1 Announce Type: cross Abstract: Deep neural networks often fail at small-sample regression, collapsing to low-variance predictions that miss individual differences. Here, we introduce a pairwise compari…
- arXiv cs.AIagentsCovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation
arXiv:2610.27677v1 Announce Type: cross Abstract: In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense…
- arXiv cs.AIresearchVLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs
arXiv:2610.27698v1 Announce Type: cross Abstract: Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in…
- arXiv cs.AIresearchBeyond Calibration: Temporal LLM Confidence Assessment Across Languages and Local Settings
arXiv:2610.27702v1 Announce Type: cross Abstract: Large language models are expected to estimate their own uncertainty, with confidence signals used to guide retrieval, adaptive compute allocation, routing, and selective…
- arXiv cs.AIresearchRLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
arXiv:2610.27712v2 Announce Type: replace-cross Abstract: Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate w…
- arXiv cs.AIresearchWorld2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation
arXiv:2610.27725v1 Announce Type: cross Abstract: Long-horizon human-object-scene interaction (HOSI) is central to embodied AI, animation, and game development. Existing human-object interaction (HOI) and human-scene int…
- arXiv cs.AIresearchAnytime-Valid Runtime Monitoring of Learned Barrier Certificates
arXiv:2610.27726v1 Announce Type: cross Abstract: Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the u…
- arXiv cs.AIagentsHearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates
arXiv:2610.27745v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judgment assistants and as stand-in participants in psychology experiments, yet little is known about how much their…
- arXiv cs.AIagentsS$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with a 500-Million-Persona Resource
arXiv:2610.27746v5 Announce Type: replace-cross Abstract: Simulating economic responses at society scale requires decision rules that respond to household circumstances and accounting rules that track their consequences.…
- arXiv cs.AIresearchHow Much Do $\ell_1$ Attacks Need Concentrated Perturbations?
arXiv:2610.27773v1 Announce Type: cross Abstract: A global $\ell_1$ budget limits how much an adversary may change an image, not how that change is distributed. We ask how much of an $\ell_1$ attack's observed success re…
- arXiv cs.AIresearchRadar-Based 3D Human Pose Estimation via Motion-Aware Pose Initialization and Observation-Guided Refinement
arXiv:2610.27774v1 Announce Type: cross Abstract: 3D Human Pose Estimation (3D HPE) is used in indoor environments, such as smart homes, to analyze human movement and monitor human states. Millimeter-wave (mmWave) radar…
- arXiv cs.AIagentsRELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic Repair
arXiv:2610.27784v1 Announce Type: cross Abstract: Vulnerability benchmarks and software engineering research depend on rebuilding historical software. Yet builds rely on external resources, such as base images and packag…
- arXiv cs.AIresearchSLM-SS: Token-Based Speech Separation with Speech Language Models
arXiv:2610.27785v1 Announce Type: cross Abstract: Speech separation (SS) has witnessed substantial progress in recent years with the advent of neural network-based methods, achieving notable improvements on signal-level…
- arXiv cs.AIresearchRAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis
arXiv:2610.27816v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitione…
- arXiv cs.AIresearchSMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual Rubrics
arXiv:2610.27820v1 Announce Type: cross Abstract: Word error rate (WER) assigns equal cost to lexical edits despite their different semantic consequences, while overall semantic scores cannot identify which individual er…
- arXiv cs.AIresearchVISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR
arXiv:2610.27867v1 Announce Type: cross Abstract: Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hyp…
- arXiv cs.AIresearchHallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation
arXiv:2610.27868v1 Announce Type: cross Abstract: Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved cod…