AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCharacterizing Overconfident Failure in LLM-Based Code Generation
arXiv:2610.11300v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for automated code generation, but generated programs can appear syntactically plausible while still failing execution-…
- arXiv cs.AIresearchFrom Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon
arXiv:2610.11309v1 Announce Type: cross Abstract: Different optimizers can fit the same training data while selecting classifiers with substantially different geometries, but whether this difference provably affects popu…
- arXiv cs.AIresearchMetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface
arXiv:2610.11316v1 Announce Type: cross Abstract: System One models output constrained decisions and probability distributions rather than free-form text generation. While prevailing paradigms rely on structured schema o…
- arXiv cs.AIresearchRethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
arXiv:2610.11374v2 Announce Type: replace-cross Abstract: CLIP serves as a foundational vision-language model and the de facto vision encoder for downstream VLMs such as LLaVA. Post-training offers a lightweight route to…
- arXiv cs.AIresearchCRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
arXiv:2610.11376v2 Announce Type: replace-cross Abstract: Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points flo…
- arXiv cs.AIresearchEvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection
arXiv:2610.11381v1 Announce Type: cross Abstract: AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is cha…
- arXiv cs.AIresearchRISR: Residual-Informed Scientific Equation Discovery with Large Language Models
arXiv:2610.11387v1 Announce Type: cross Abstract: Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce…
- arXiv cs.AIresearchRewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer
arXiv:2610.11416v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vi…
- arXiv cs.AIresearchMissing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation
arXiv:2610.11419v1 Announce Type: cross Abstract: Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol hetero…
- arXiv cs.AIagentsClosed-loop evaluation of LLM agents for embedded software development
arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively.…
- arXiv cs.AIresearchZatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains
arXiv:2610.11454v2 Announce Type: replace-cross Abstract: Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-…
- arXiv cs.AIresearchGenerative Adversarial Loops
arXiv:2610.11458v1 Announce Type: cross Abstract: AI research progress can be viewed as the interaction between two processes: benchmark creation and method discovery. Historically, both were driven by human intelligence…
- arXiv cs.AIresearchProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification
arXiv:2610.11460v1 Announce Type: cross Abstract: Prototypes in classification models are almost always vectors, and a vector has no readable form. This paper asks what happens when a prototype is an image. Documents giv…
- arXiv cs.AIagentsGROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
arXiv:2610.11467v1 Announce Type: cross Abstract: We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable.…
- arXiv cs.AIresearchConditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher
arXiv:2610.11479v1 Announce Type: cross Abstract: Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation. Under standard training, however, they often…
- arXiv cs.AIagentsRoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes
arXiv:2610.11480v1 Announce Type: cross Abstract: Embodied coding agents can combine modular robot skills with frozen end-to-end policies, yet effective composition requires anticipating which policy family will succeed…
- arXiv cs.AIagentsEvaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows
arXiv:2610.11482v1 Announce Type: cross Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents rem…
- arXiv cs.AIresearchCompactness and Consistency: A Conjoint Framework for Deep Graph Clustering
arXiv:2610.11506v1 Announce Type: cross Abstract: Graph clustering is a fundamental task in data analysis, aiming at grouping nodes with similar characteristics in the graph into clusters. This problem has been widely ex…
- arXiv cs.AIresearchMSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval
arXiv:2610.11526v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer an energy-efficient computing paradigm through sparse event-driven computation, showing great potential for efficient multimodal lear…
- arXiv cs.AIresearchDesign Creativity Bench: Measuring creativity in LLM-Generated UI
arXiv:2610.11539v2 Announce Type: replace-cross Abstract: As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised. Our work i…
- arXiv cs.AIagentsConstitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
arXiv:2610.11542v3 Announce Type: replace-cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance…
- arXiv cs.AIresearchLearning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating
arXiv:2610.11546v2 Announce Type: replace-cross Abstract: Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated parameters.…
- arXiv cs.AIagentsSWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in tas…
- arXiv cs.AIresearchSera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting
arXiv:2610.11567v3 Announce Type: replace-cross Abstract: Battery state of health (SoH) forecasting is important for battery management, but remains challenging due to nonlinear degradation and heterogeneity across batte…
- arXiv cs.AIagentsSDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
arXiv:2610.11583v1 Announce Type: cross Abstract: End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (…
- arXiv cs.AIresearchAdapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection
arXiv:2610.11585v1 Announce Type: cross Abstract: Recent advances in large language model (LLM) pretraining highlight the role of high-quality training data in improving performance. While model-based filtering has prove…
- arXiv cs.AIagentsRunnable Commit Untangling for Coding Agents
arXiv:2610.11593v1 Announce Type: cross Abstract: Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of…
- arXiv cs.AIresearchLarge Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
arXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this screening rests on benchm…
- arXiv cs.AIresearchNanoProof: Open and Efficient Automated Theorem Proving in Lean 4
arXiv:2610.11605v1 Announce Type: cross Abstract: We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, training pipeline, and we…
- arXiv cs.AIresearchBeyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence
arXiv:2610.11610v1 Announce Type: cross Abstract: Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of the dynamic examinati…
- arXiv cs.AIresearchTAM: Task-Aware Memory Distillation for Efficient Spatiotemporal Prediction
arXiv:2610.11617v1 Announce Type: cross Abstract: Knowledge distillation enables efficient spatiotemporal prediction by transferring knowledge from an accurate teacher to a compact student. However, matching outputs or f…
- arXiv cs.AIresearchNeural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control
arXiv:2610.11631v1 Announce Type: cross Abstract: Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a s…
- arXiv cs.AIresearchLTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
arXiv:2610.11634v1 Announce Type: cross Abstract: Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in…
- arXiv cs.AIagentsOne Skill Too Many: How Co-Installed Skills Conflict in Coding Agents
arXiv:2610.11647v2 Announce Type: replace-cross Abstract: Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from independent sour…
- arXiv cs.AIagentsSkillContrast: Difference-Guided Text Selection for Agent Skill Reranking
arXiv:2610.11650v1 Announce Type: cross Abstract: Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit these distinctions.…
- arXiv cs.AIresearchDIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation
arXiv:2610.11659v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals. Its sampled-token variant avoids the cost of full-vocabulary prob…
- arXiv cs.AIresearchHI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution
arXiv:2610.11685v2 Announce Type: replace-cross Abstract: Image-to-3D generation has become increasingly capable of producing objects that closely resemble the input image, and an outstanding challenge is to reproduce th…
- arXiv cs.AIresearchEpistemic Disturbance in the Graph Model for Conflict Resolution: State-Preserving Actions, Four-Valued Assessments, and the Distinction between Capability and Intention
arXiv:2610.11690v1 Announce Type: cross Abstract: In the graph model for conflict resolution (GMCR), a decision maker (DM) either moves the conflict to another state or does nothing. The basic definitions leave inaction…
- arXiv cs.AIresearchCan Jev be Your Q or Policy in Reinforcement Learning?
arXiv:2610.11692v1 Announce Type: cross Abstract: Foundation models supply reinforcement learning (RL) with priors that mitigate its longstanding weaknesses in sample efficiency and transfer, but their token-by-token gen…
- arXiv cs.AIresearchElucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model
arXiv:2610.11694v1 Announce Type: cross Abstract: Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function. We formula…
- arXiv cs.AIresearchMAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning
arXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However,…
- arXiv cs.AIresearchTimer-M1: A Multivariate Time Series Foundation Model via Learning Primitives
arXiv:2610.11734v1 Announce Type: cross Abstract: We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share ele…
- arXiv cs.AIresearchUncovering and Fixing Collider Bias in Bayesian PINNs
arXiv:2610.11737v2 Announce Type: replace-cross Abstract: Bayesian physics-informed neural networks (B-PINNs) are a popular framework for parameter and state inference from sparse or noisy observations. They are commonly…
- arXiv cs.AIresearchDEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference
arXiv:2610.11748v2 Announce Type: replace-cross Abstract: U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dynamically rath…
- arXiv cs.AIresearchSame Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
arXiv:2610.11766v1 Announce Type: cross Abstract: Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcome can arise for very…
- arXiv cs.AIagentsNarrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System
arXiv:2610.11768v1 Announce Type: cross Abstract: Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about the plant. Established…
- arXiv cs.AIresearchAuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance
arXiv:2610.11792v1 Announce Type: cross Abstract: We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive mo…
- arXiv cs.AIresearchFrom Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction
arXiv:2610.11818v1 Announce Type: cross Abstract: While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limits adoption in instit…
- arXiv cs.AIresearchFrom Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment
arXiv:2610.11826v1 Announce Type: cross Abstract: Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content. An intuitive mitigation strategy is to suppress hallu…
- arXiv cs.AIresearchGRPODropout: Less is More for Online Reinforcement Learning Rollouts
arXiv:2610.11854v1 Announce Type: cross Abstract: Reinforcement learning (RL) methods such as GRPO substantially improve large language model reasoning but often suffer from policy entropy collapse: the loss of sampling…