AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAn Informational Curse of Horizon in Goal-Conditioned Policy Learning
arXiv:2610.09247v1 Announce Type: cross Abstract: The difficulty of learning goal-reaching policies is often attributed to a "curse of horizon" that manifests as bias accumulation in temporal-difference backups and noisy…
- arXiv cs.AIresearchEfficient Best-of-N policy evaluation for inference-time alignment
arXiv:2610.09250v1 Announce Type: cross Abstract: Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model. Evaluating BoN policies from…
- arXiv cs.AIresearchEvaluating Trajectory Features for Routing Final-Layer Attention
arXiv:2610.09272v1 Announce Type: cross Abstract: Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, curvature and error…
- arXiv cs.AIresearchNode-level Graph Neural Architecture Search Framework
arXiv:2610.09297v1 Announce Type: cross Abstract: In recent years, Graph Neural Networks (GNNs) and architecture search frameworks have gained extensive application in non-Euclidean data processing, attributable to their…
- arXiv cs.AIresearchKuration SDK: Addressing the Virtual2Real Gap via Data Curation
arXiv:2610.09305v1 Announce Type: cross Abstract: Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and p…
- arXiv cs.AIresearchDenoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization
arXiv:2610.09311v1 Announce Type: cross Abstract: Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. Howe…
- arXiv cs.AIresearchConstrained Diffusion for Data-Scarce Orbital Monte Carlo in Constellation Tasking
arXiv:2610.09323v1 Announce Type: cross Abstract: Constellation Monte Carlo results depend on the orbital population used to evaluate a tasking policy. With scarce reference trajectories, replay limits geometric diversit…
- arXiv cs.AIresearchVisual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation
arXiv:2610.09328v1 Announce Type: cross Abstract: Multi-subject image generation requires rewards that verify whether requested attributes, actions, and relations hold for the specified reference subjects. Subject presen…
- arXiv cs.AIresearchShared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression
arXiv:2610.09342v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models decouple capacity from compute through sparse routing, but their large parameter count creates storage and serving challeng…
- arXiv cs.AIresearchOnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models
arXiv:2610.09346v1 Announce Type: cross Abstract: Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, ar…
- arXiv cs.AIresearchMultimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding
arXiv:2610.09355v1 Announce Type: cross Abstract: Learning EEG representations that generalize across cognitive tasks, subjects, and recording conditions remains a key challenge in electroencephalography (EEG) decoding.…
- arXiv cs.AIresearchFrom Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
arXiv:2610.09361v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not mode…
- arXiv cs.AIresearchTutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback
arXiv:2610.09400v1 Announce Type: cross Abstract: We present TutorLoop, a sensor-in-the-loop system that regulates student learning behaviors by delivering adaptive feedback based on real-time cognitive states. Unlike pr…
- arXiv cs.AIresearchShared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
arXiv:2610.09411v2 Announce Type: replace-cross Abstract: Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data.…
- arXiv cs.AIresearchMixture of Layers: Dynamic Layer Routing for Visual Reasoning
arXiv:2610.09440v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local details.…
- arXiv cs.AIresearchArctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science
arXiv:2610.09446v1 Announce Type: cross Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not demonstrate sensitiv…
- arXiv cs.AIresearchIris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
arXiv:2610.09450v1 Announce Type: cross Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim a…
- arXiv cs.AIresearchGeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
arXiv:2610.09456v1 Announce Type: cross Abstract: Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly…
- arXiv cs.AIresearchDSReg: Provably Recovering Individual World Latents without Reconstruction
arXiv:2610.09457v1 Announce Type: cross Abstract: Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observa…
- arXiv cs.AIresearchMORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection
arXiv:2610.09473v1 Announce Type: cross Abstract: Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies c…
- arXiv cs.AIresearchCorrespondences as Decisions: JevNexus for Decision-Centric Schema Matching
arXiv:2610.09487v1 Announce Type: cross Abstract: Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We…
- arXiv cs.AIresearchSparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
arXiv:2610.09496v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. Ho…
- arXiv cs.AIresearchSpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models
arXiv:2610.09498v1 Announce Type: cross Abstract: Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \textbf{SpatialUQ…
- arXiv cs.AIresearchSafe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable?
arXiv:2610.09508v1 Announce Type: cross Abstract: Safe reinforcement learning seeks policies that maximize return while satisfying constraints on cumulative cost. Most methods impose these constraints on expected episodi…
- arXiv cs.AIresearchOmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning
arXiv:2610.09513v2 Announce Type: replace-cross Abstract: Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene…
- arXiv cs.AIresearchAlign Before You Combine: Reference Space Calibration for Supervision Without Ground Truth
arXiv:2610.09525v1 Announce Type: cross Abstract: We introduce a calibration-first framework that produces supervision scores without access to ground-truth labels or a shared annotation space. Our framework aligns subse…
- arXiv cs.AIresearchKASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
arXiv:2610.09534v1 Announce Type: cross Abstract: Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation. However, current symmetry annotations f…
- arXiv cs.AIresearchWAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation
arXiv:2610.09535v1 Announce Type: cross Abstract: Real-world applications require 6D pose estimation to be accurate, fast, and scalable to unseen objects. This paper introduces WAPR, a zero-shot wide-angle pose refinemen…
- arXiv cs.AIresearchMARS: Malware Analysis with Rule-Based Scoring of LLM Claims
arXiv:2610.09553v1 Announce Type: cross Abstract: Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy. We present MARS, a malware triage framework, and compa…
- arXiv cs.AIresearchHow Do LLMs Change Predictions Under Negation?
arXiv:2610.09571v2 Announce Type: replace-cross Abstract: Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source and closed…
- arXiv cs.AIresearchCollaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
arXiv:2610.09587v1 Announce Type: cross Abstract: Reasoning capabilities are critical for advancing Large Language Models, yet current approaches either require massive computational budgets or struggle to effectively di…
- arXiv cs.AIresearchAdaptive Code Generation for Controlling Robots
arXiv:2610.09588v1 Announce Type: cross Abstract: Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based auton…
- arXiv cs.AIresearchStructured pre-generation elicitation versus single-shot prompting in AI-assisted enterprise decision-making: a randomised online experiment
arXiv:2610.09593v1 Announce Type: cross Abstract: Generative AI speeds, and mostly improves, professional work, but there is concern that users who delegate both the production and the evaluation of an answer may accept…
- arXiv cs.AIresearchWhich Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
arXiv:2610.09607v1 Announce Type: cross Abstract: Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We prop…
- arXiv cs.AIresearchReal-world application of deep learning in large-scale seismic interference attenuation: A case study in the Camie field of Angola
arXiv:2610.09663v1 Announce Type: cross Abstract: In marine seismic acquisition, seismic interference (SI) occurs when energy from nearby external seismic source(s) is captured. It typically appears as coherent noise wit…
- arXiv cs.AIresearchCERO: Where and When to Allocate Rollouts for RL Post-Training
arXiv:2610.09679v1 Announce Type: cross Abstract: Adaptive rollout methods for group-relative reinforcement learning typically allocate a fixed per-update budget across prompts. We instead study how to coordinate a finit…
- arXiv cs.AIresearchFew-Shot Learning for Personalised Automated Pain Assessment
arXiv:2610.09692v1 Announce Type: cross Abstract: Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dataset. One way to a…
- arXiv cs.AIresearchWhat Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?
arXiv:2610.09700v2 Announce Type: replace-cross Abstract: Synthetic hard negatives generated in the representation space have proven effective for unimodal self-supervised learning, but transferring this idea to vision-l…
- arXiv cs.AIresearchHealthy skepticism in AI: a data visualization research agenda
arXiv:2610.09740v1 Announce Type: cross Abstract: Research in data visualization of artificial intelligence (AI) models has historically focused on enhancing trust through visual explanations of AI. The trustworthiness l…
- arXiv cs.AIresearchUnrolled Flow Models for Reasoning
arXiv:2610.09759v1 Announce Type: cross Abstract: Flow matching enables language generation in few steps, but whether additional integration steps improve reasoning remains unclear. We prove that a flow parameterized by…
- arXiv cs.AIresearchPARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency
arXiv:2610.09761v1 Announce Type: cross Abstract: Text-to-point-cloud localization estimates a position in a city-scale 3D map from descriptions of surrounding objects. Existing coarse-to-fine methods retrieve submaps us…
- arXiv cs.AIresearchArtificial intelligence pathways from weather to climate
arXiv:2610.09770v1 Announce Type: cross Abstract: Deep learning has made rapid advances in weather forecasting: autoregressive models trained on atmospheric reanalyses now rival dynamical models across nowcasting, medium…
- arXiv cs.AIresearchMIRROR: From Imitation to Internalization in LLM Personalization
arXiv:2610.09795v1 Announce Type: cross Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap in existing fine-tu…
- arXiv cs.AIresearchDisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
arXiv:2610.09802v1 Announce Type: cross Abstract: Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. Howev…
- arXiv cs.AIresearchUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
arXiv:2610.09823v1 Announce Type: cross Abstract: Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, e…
- arXiv cs.AIresearchA Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks
arXiv:2610.09835v1 Announce Type: cross Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using often-inaccessible o…
- arXiv cs.AIresearchFully Interpretable Minimal Transformers: From Geometry to Algorithm
arXiv:2610.09838v1 Announce Type: cross Abstract: We present a framework for building and interpreting minimal transformer models. By constraining a transformer's embedding dimension and head size to 2, we enable full tw…
- arXiv cs.AIresearchStream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study
arXiv:2610.09848v1 Announce Type: cross Abstract: Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large dataset is…
- arXiv cs.AIresearchA Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
arXiv:2610.09891v1 Announce Type: cross Abstract: Human-Robot Collaboration (HRC) can facilitate mass customisation in Industry 4.0, with Reinforcement Learning from Human Feedback (RLHF) representing a promising approac…
- arXiv cs.AIresearchDefensive Sufficiency in a Stackelberg Model of AI Security
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead to effective repair…