AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchReinforcement Learning from Real-Robot Interaction without High-Quality State Estimates
arXiv:2610.14042v1 Announce Type: cross Abstract: A longstanding goal for robot reinforcement learning (RL) is that robots learn from their own physical experience, as humans and animals do. A key obstacle to learning di…
- arXiv cs.AIresearchThe Future of AI-assisted Physics: Discovering, Verifying and Organizing Results via Formalization
arXiv:2610.14059v1 Announce Type: cross Abstract: Rapid advances in AI have opened a new era for physics, enabling unprecedented capabilities in research and discovery. However, these advances also bring challenges in ve…
- arXiv cs.AIresearchIs the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, committing to specific…
- arXiv cs.AIresearchOne Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns
arXiv:2610.14074v1 Announce Type: cross Abstract: Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interactions, however, com…
- arXiv cs.AIresearchEmbodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic Manipulation
arXiv:2610.14106v1 Announce Type: cross Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded decisions that res…
- arXiv cs.AIresearchBeyond Discrimination: Evaluating Probability Calibration in Radiomics-Image Fusion for Renal Cell Carcinoma Classification
arXiv:2610.14151v1 Announce Type: cross Abstract: Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics--image fusion models for renal cell carcinoma…
- arXiv cs.AIresearchBeyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification
arXiv:2610.14152v1 Announce Type: cross Abstract: Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contributions at the classifier o…
- arXiv cs.AIresearchNext-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
arXiv:2610.14162v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as inference becomes a domi…
- arXiv cs.AIresearchDo you "see" what I "see"? A Multi-panel Visual Question Answer Dataset for Large Language Model Chart Analysis
arXiv:2610.14173v1 Announce Type: cross Abstract: Digital libraries increasingly host scientific publications whose figures encode primary research findings, yet making this visual content searchable, accessible, and reu…
- arXiv cs.AIresearchLearnable Low-Rank Polynomial Sketch for Effective Linear Attention
arXiv:2610.14219v1 Announce Type: cross Abstract: Softmax attention in Transformers suffers from quadratic complexity in sequence length, making it impractical for long-context applications. Linear attention alleviates t…
- arXiv cs.AIresearchCAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT
arXiv:2610.14226v1 Announce Type: cross Abstract: Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. Materials & Methods…
- arXiv cs.AIresearchAkule: Fast and Scalable Multi-Robot Motion Planning via Sparse Interaction Diffusion
arXiv:2610.14248v1 Announce Type: cross Abstract: Diffusion models provide expressive trajectory priors for multi-robot motion planning (MRMP), but scaling them to large teams requires coordinating individual motions wit…
- arXiv cs.AIresearchThe RNN Homunculus: Learning to Gate Long-Term Memory
arXiv:2610.14279v1 Announce Type: cross Abstract: Learning long-range dependencies with recurrent neural networks (RNNs) is difficult because of the vanishing gradient problem. Gated recurrent neural networks like GRUs a…
- arXiv cs.AIresearchGeoFix: Geometry Fixing for 4D Consistent Generation
arXiv:2610.14293v1 Announce Type: cross Abstract: Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through p…
- arXiv cs.AIresearchRUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can
arXiv:2610.14299v1 Announce Type: cross Abstract: Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on this foundation, recen…
- arXiv cs.AIresearchMvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
arXiv:2610.14315v2 Announce Type: replace-cross Abstract: Reconstructing accurate camera poses and floor-plan layouts from sparse, unposed, wide-baseline RGB panoramas remains a challenging open problem. Direct multi-roo…
- arXiv cs.AIresearchEV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference
arXiv:2610.14324v2 Announce Type: replace-cross Abstract: Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones, robots, and servers. Yet, they…
- arXiv cs.AIresearchTraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative Sampling
arXiv:2610.14332v1 Announce Type: cross Abstract: Accurate sampling from continuous-time generative models can require many model evaluations. Low-step sampling reduces cost, but coarse updates introduce endpoint errors…
- arXiv cs.AIresearchDexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity
arXiv:2610.14372v1 Announce Type: cross Abstract: Dexterous robot hands can receive useful motion intent from teleoperation or learned policies, but successful execution also depends on contact decisions that these comma…
- arXiv cs.AIresearchDeep learning from a control vantage point
arXiv:2610.14385v1 Announce Type: cross Abstract: This article offers an overview of recent developments in deep learning from a control vantage point. It reviews several classes of models including feedforward and resid…
- arXiv cs.AIresearchMemory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies
arXiv:2610.14406v1 Announce Type: cross Abstract: It is widely appreciated that robotic policies require long-term memory to perform complex tasks. However, directly conditioning policies on all past observations leaves…
- arXiv cs.AIresearchCoarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes
arXiv:2610.14413v1 Announce Type: cross Abstract: Computational coarse-graining aims to replace a sequence of updates with a cheaper module while preserving task performance. We present a continuation-relative evaluation…
- arXiv cs.AIresearchSceneForesee: Learning Scene Evolution for Spatiotemporal Reasoning
arXiv:2610.14439v1 Announce Type: cross Abstract: Large multimodal models (LMMs) need to understand how entities move and interact as a scene develops. This requires following the same entities over time and relating the…
- arXiv cs.AIresearchTarget-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling
arXiv:2610.14440v1 Announce Type: cross Abstract: Asynchronous reinforcement-learning post-training of large language models is computationally efficient but inherently off-policy: the learner updates on rollouts generat…
- arXiv cs.AIresearchSpecification-Based Testing of Large Language Models
arXiv:2610.14443v1 Announce Type: cross Abstract: Model cards, system cards, and safety reports increasingly document LLM safety behaviors, yet safety evaluations typically start from predefined benchmarks rather than as…
- arXiv cs.AIresearchKV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization
arXiv:2610.14448v1 Announce Type: cross Abstract: Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail generation. Sustained…
- arXiv cs.AIresearchCo-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval
arXiv:2610.14465v2 Announce Type: replace-cross Abstract: Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retr…
- arXiv cs.AIresearchDiffusion-Based Auctions for Multi-Winner Banner Ads
arXiv:2610.14473v1 Announce Type: cross Abstract: We propose a new framework for banner ad auctions, leveraging diffusion models to allow for multiple bidders to co-win a single banner ad opportunity, and in particular i…
- arXiv cs.AIresearchRES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation
arXiv:2610.14474v1 Announce Type: cross Abstract: Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decision-making and personal…
- arXiv cs.AIresearchScale, Drivers, and Limits of Representational Alignment Across Large Language Models
arXiv:2610.14476v1 Announce Type: cross Abstract: Comparing large language models can reveal shared representational structure and systematic differences between them. However, aggregate similarity measures can obscure h…
- arXiv cs.AIresearchAphaVoice: Text-to-Speech Model for Aphasia Patient Simulation
arXiv:2610.14479v1 Announce Type: cross Abstract: While language therapy is the primary treatment for post-stroke aphasia, limited clinical resources often restrict patient access to proper care. Addressing this gap requ…
- arXiv cs.AIresearchRethinking Activation Functions: Reducing Bias Can Improve Learning
arXiv:2610.14500v1 Announce Type: cross Abstract: Many widely used activation functions, including ReLU, GELU, Swish, and Sigmoid, produce predominantly positive outputs, resulting in a nonzero post-activation mean that…
- arXiv cs.AIresearchCompositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning
arXiv:2610.14514v1 Announce Type: cross Abstract: Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of machine unlearning to…
- arXiv cs.AIresearchWho to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation
arXiv:2610.14530v1 Announce Type: cross Abstract: Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tasks in complex environ…
- arXiv cs.AIresearchGG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models
arXiv:2610.14541v1 Announce Type: cross Abstract: Emerging strong Vision-Language Models (VLMs) have advanced navigation foundation models. However, these models still have unsatisfactory performance on goal-oriented nav…
- arXiv cs.AIresearchLLM-based User-Product Relevance Evaluation for Dynamic Product Advertising
arXiv:2610.14550v1 Announce Type: cross Abstract: Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challenging. Conventional off…
- arXiv cs.AIresearchLASER: Defeasible Certificate Search for Long-Range Protocol Dependencies
arXiv:2610.14552v1 Announce Type: cross Abstract: Protocol specifications rarely justify executable behavior in one place: a transition may inherit its source state from a remote control block, name its events only by nu…
- arXiv cs.AIresearchLimitations on Autoregressive Token Generation via Sequential Sampling
arXiv:2610.14615v2 Announce Type: replace-cross Abstract: We study autoregressive token generation through the notion of sequential samplers: A circuit that samples the next symbol only given the previous ones and possib…
- arXiv cs.AIresearchEarthAlign: Learning Language-Aligned Representations of Earth System Data
arXiv:2610.14624v1 Announce Type: cross Abstract: Interpreting Earth system conditions is central to understanding environmental risks and informing decisions across weather- and climate-sensitive sectors. Existing multi…
- arXiv cs.AIresearchProspective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
arXiv:2610.14654v1 Announce Type: cross Abstract: Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited pred…
- arXiv cs.AIresearchDexCast: Learning Real-World Dexterous Control from Human Videos
arXiv:2610.14691v2 Announce Type: replace-cross Abstract: Recent advances in 3D hand-object interaction (HOI) perception have opened new opportunities for learning dexterous robotic skills from human videos. However, exi…
- arXiv cs.AIresearchAlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation
arXiv:2610.14697v1 Announce Type: cross Abstract: Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity in clean acoustic c…
- arXiv cs.AIresearchTowards Merging-conditional Backdoor Unalignment against Large Language Models
arXiv:2610.14701v1 Announce Type: cross Abstract: Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training. While the specialized mod…
- arXiv cs.AIresearchLingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
arXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging because prescription de…
- arXiv cs.AIresearchIntegrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient
arXiv:2610.14723v1 Announce Type: cross Abstract: A method integrating policy gradient with fuzzy inference has been proposed. This method, hereafter referred to as the base model, has high flexibility with respect to th…
- arXiv cs.AIresearchPrior-Fitted and Frozen Scorers for Multimodal Contrastive Learning
arXiv:2610.14770v1 Announce Type: cross Abstract: Multimodal contrastive learning typically relies on manually specified scoring functions, such as cosine similarity, to quantify the similarity between representations fr…
- arXiv cs.AIresearchTraining a Compact, Strong, and Realistic Text-to-Speech Model
arXiv:2610.14776v1 Announce Type: cross Abstract: Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity. However, neither objective captures the prosodic detail that disting…
- arXiv cs.AIresearchDepth-progressive 3D seismic velocity model building via 2D generative diffusion models
arXiv:2610.14812v1 Announce Type: cross Abstract: Three-dimensional (3D) velocity model building (VMB) remains computationally challenging with conventional approaches and native 3D neural networks, largely due to the pr…
- arXiv cs.AIresearchSeamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance
arXiv:2610.14815v1 Announce Type: cross Abstract: Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architectures send all raw te…
- arXiv cs.AIresearchAI-Native Product Management: A Vision
arXiv:2610.14823v1 Announce Type: cross Abstract: Artificial intelligence is increasingly used to support product management tasks. At the same time, AI-native research and development (R&D) may increase software realiza…