AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- 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.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.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…
- arXiv cs.AIresearchEvaluating Exact Output and Checkpoint-State Prediction in Real Programs
arXiv:2610.11889v1 Announce Type: cross Abstract: We present a benchmark for predicting final output and checkpoint state from source and input alone. It extends CRUXEval-style output prediction with paired shorter- and…
- arXiv cs.AIresearchBeyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
arXiv:2610.11907v1 Announce Type: cross Abstract: Hallucination remains a significant challenge in Large Vision-Language Models (LVLMs). Existing training-free methods generally mitigate hallucinations through contrastiv…
- arXiv cs.AIresearchFrom Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
arXiv:2610.11918v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding. However, reasoning based mainly on observable af…
- arXiv cs.AIresearchNeural Decoding as Cognitive Inference
arXiv:2610.11923v1 Announce Type: cross Abstract: The brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observations remains a cen…
- arXiv cs.AIresearchStochastic Grouping Conformal Prediction for Effective Subgroup Reliability
arXiv:2610.11957v2 Announce Type: replace-cross Abstract: Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, howe…
- arXiv cs.AIresearchDataVista: Diagnosing Multimodal LLMs on Data Video Understanding
arXiv:2610.11993v1 Announce Type: cross Abstract: Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video un…
- arXiv cs.AIresearchNeural Network Verification for Deep Joint Source-Channel Coding
arXiv:2610.11994v1 Announce Type: cross Abstract: Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharpl…
- arXiv cs.AIresearchThe Polytopal Neural Network
arXiv:2610.12004v1 Announce Type: cross Abstract: Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on pr…
- arXiv cs.AIresearchREACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
arXiv:2610.12007v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-of…
- arXiv cs.AIresearchHWAM: Humanoid World Action Model With Joint State--Action Generation
arXiv:2610.12026v2 Announce Type: replace-cross Abstract: Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from multimodal obs…
- arXiv cs.AIresearchTraceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems
arXiv:2610.12033v1 Announce Type: cross Abstract: Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confidence and potential r…
- arXiv cs.AIresearchMPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation
arXiv:2610.12039v1 Announce Type: cross Abstract: Graph neural networks (GNNs) predict molecular properties from chemical graph data, but predictive accuracy does not explain how graph information supports an individual…
- arXiv cs.AIresearchMAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
arXiv:2610.12067v1 Announce Type: cross Abstract: Elucidating molecular structures from spectra is a foundational problem in chemical and materials characterization, yet remains challenging due to spectral ambiguity and…
- arXiv cs.AIresearchAll Verdicts are Not Equal: Rethinking LLM Judge Reliability
arXiv:2610.12083v1 Announce Type: cross Abstract: LLM-as-a-Judge is the standard paradigm for NLP evaluation, yet its systemic reliability remains poorly understood despite being widely treated as a deterministic ground…
- arXiv cs.AIresearchVINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
arXiv:2610.12104v1 Announce Type: cross Abstract: Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are prohibitively expens…
- arXiv cs.AIresearchA Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
arXiv:2610.12113v2 Announce Type: replace-cross Abstract: Actor--critic methods in reinforcement learning control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere,…
- arXiv cs.AIresearchUsing Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation
arXiv:2610.12119v1 Announce Type: cross Abstract: Algorithm Selection is essential for efficient Constraint Programming. Over the years, many algorithm selectors based on machine learning methods have been successfully a…
- arXiv cs.AIresearchLVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
arXiv:2610.12127v1 Announce Type: cross Abstract: Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaussian Splatting never…
- arXiv cs.AIresearchScalable Hierarchical Graph Generation via Soft Community Structure
arXiv:2610.12163v1 Announce Type: cross Abstract: Generating large attributed graphs requires reproducing the topology, generating attributes jointly with the structure, and remaining scalable. Many real-world graphs exi…
- arXiv cs.AIresearchUnifying Policy Learning and State Prediction through Spatial Language Modeling
arXiv:2610.12172v1 Announce Type: cross Abstract: Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modeling, which represents…
- arXiv cs.AIresearchAI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware
arXiv:2610.12182v2 Announce Type: replace-cross Abstract: Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover a tiny frac…
- arXiv cs.AIresearchVibeEdit: Image Editing with Canvas Instructions
arXiv:2610.12229v1 Announce Type: cross Abstract: In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when sev…
- arXiv cs.AIresearchFrom Prompting to Composing: A Spatial Canvas Interface for Poster Generation
arXiv:2610.12230v1 Announce Type: cross Abstract: Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of…
- arXiv cs.AIresearchReSI: Recursive Safety Improvement toward Resistant and Resilient AI
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both c…
- arXiv cs.AIresearchLa-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
arXiv:2610.12236v1 Announce Type: cross Abstract: RNA function arises from the coupling of nucleotide sequence and three-dimensional structure, motivating their joint design. Coordinating global folding with nucleotide-l…
- arXiv cs.AIresearchAdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting
arXiv:2610.12240v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Existing all-in-one met…
- arXiv cs.AIresearchBatch Before You Lift: Scalable Topological Deep Learning on Large Graphs
arXiv:2610.12247v1 Announce Type: cross Abstract: Topological Deep Learning extends graph-based learning to higher-order domains, such as hypergraphs, cellular, and simplicial complexes. These domains are typically const…
- arXiv cs.AIresearchReal-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
arXiv:2610.12249v1 Announce Type: cross Abstract: We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rather than introducing…
- arXiv cs.AIresearchHow Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders
arXiv:2610.12250v1 Announce Type: cross Abstract: Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their usefulness depends partly on which signal propertie…
- arXiv cs.AIresearchSyn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings
arXiv:2610.12256v1 Announce Type: cross Abstract: Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal embedding metho…
- arXiv cs.AIresearchMachine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery
arXiv:2610.12293v1 Announce Type: cross Abstract: Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incorporated more directly into data analysis, simulati…
- arXiv cs.AIresearchPrediction-Powered Data Fusion for Treatment Effect Estimation
arXiv:2610.12332v2 Announce Type: replace-cross Abstract: Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observational studies (OBS) are large but may be c…
- arXiv cs.AIresearchRiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local…
- arXiv cs.AIresearchContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration
arXiv:2610.12337v1 Announce Type: cross Abstract: Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variations in slice sampling…