AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchLENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis
arXiv:2610.00294v1 Announce Type: cross Abstract: Automated acne severity grading requires both whole-face context and fine-grained lesion evidence. We propose LENS-GRF (Lesion Evidence Network with Set-Transformer and G…
- arXiv cs.AIresearchCertainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning
arXiv:2610.00296v1 Announce Type: cross Abstract: Token-level certainty is widely used as a proxy for correctness in LLM training and inference. However, the performance of certainty-based methods depends both on the inf…
- arXiv cs.AIresearchDecoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping
arXiv:2610.00302v1 Announce Type: cross Abstract: Crowdsourced imagery provides timely, fine-grained, street-level observations for disaster mapping, complementing conventional remote sensing imagery (RSI) during emergen…
- arXiv cs.AIresearchTokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs
arXiv:2610.00309v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity to memorize and discl…
- arXiv cs.AIresearchBeyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents
arXiv:2610.00315v1 Announce Type: cross Abstract: Historical Manchu documents preserve invaluable linguistic and cultural heritage, yet their digitization is hindered by severe degradations and the scarcity of paired tra…
- arXiv cs.AIresearchDriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies
arXiv:2610.00317v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control. While chunk-level training is co…
- arXiv cs.AIresearchThe Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
arXiv:2610.00332v1 Announce Type: cross Abstract: Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current approaches face a fun…
- arXiv cs.AIresearchLEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation
arXiv:2610.00333v1 Announce Type: cross Abstract: Multimodal on-policy distillation (OPD) aims to improve visual grounding while preserving the strong reasoning capabilities of language models. Recent multi-teacher appro…
- arXiv cs.AIresearchDiffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength
arXiv:2610.00359v1 Announce Type: cross Abstract: Diffusion models with prompt and reference image-guided editing have seen rapid progress, yet they remain too coarse for pixel-level control. One promising direction is t…
- arXiv cs.AIresearchDeep Learning for Anomaly Detection in Railway Systems: A Structured Survey
arXiv:2610.00363v1 Announce Type: cross Abstract: Ensuring safe and reliable operation of modern railway systems increasingly relies on data-driven monitoring and intelligent fault detection. Deep learning has emerged as…
- arXiv cs.AIresearchManifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment
arXiv:2610.00365v1 Announce Type: cross Abstract: Recent advances in distillation and flow-map models have enabled deterministic one- or few-step generation for high-quality data, facilitating a new branch of reward alig…
- arXiv cs.AIresearchDeepJEPA: Scaling World Models from Within
arXiv:2610.00368v1 Announce Type: cross Abstract: World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computation to every imagined…
- arXiv cs.AIresearchA Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premium
arXiv:2610.00369v1 Announce Type: cross Abstract: Laurito et al. (PNAS 2025) showed that large language models choosing between two descriptions of the same product, paper or film prefer the description written by a lang…
- arXiv cs.AIresearchFaithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation
arXiv:2610.00374v1 Announce Type: cross Abstract: Analytical charts in multimodal deep research encode quantitative claims, requiring every visualized value to be faithfully grounded in supporting evidence. Unlike retrie…
- arXiv cs.AIresearchFAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training
arXiv:2610.00385v2 Announce Type: replace-cross Abstract: Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream lea…
- arXiv cs.AIresearchMatrixReward: Reward from Rubric Matrix for Open-Ended Generation
arXiv:2610.00389v1 Announce Type: cross Abstract: Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited information about the rela…
- arXiv cs.AIresearchInterpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps
arXiv:2610.00391v3 Announce Type: replace-cross Abstract: Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinical data is res…
- arXiv cs.AIresearchScores That Hold, Benchmarks That Leak: Measuring Dataset Contamination in Public Brain-Tumor MRI Classification
arXiv:2610.00421v1 Announce Type: cross Abstract: Automated classification of brain tumors from MRI is a heavily published application of deep learning in medical imaging, with reported accuracies on public benchmarks ro…
- arXiv cs.AIresearchLearning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon
arXiv:2610.00422v1 Announce Type: cross Abstract: Neural combinatorial optimization typically assumes a centralized solver that reads the whole instance. We study the opposite: combinatorial optimization under a hard inf…
- arXiv cs.AIresearchThe Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation
arXiv:2610.00423v2 Announce Type: replace-cross Abstract: Massive activations, residual-stream coordinates with magnitudes far larger than typical activations, are associated with attention sinks in transformers, but how…
- arXiv cs.AIresearchTarget-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model
arXiv:2610.00424v1 Announce Type: cross Abstract: Knowing how much a causal predictor could improve need not reveal the gain of the repair actually learned. We quantify this gap in a scalar Gaussian causal experiment wit…
- arXiv cs.AIresearchXOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
arXiv:2610.00432v1 Announce Type: cross Abstract: Trellis-coded quantization enables high-dimensional compression of large language model (LLM) weights at ultra-low bit widths without the exponentially large codebooks re…
- arXiv cs.AIresearchPACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video
arXiv:2610.00451v3 Announce Type: replace-cross Abstract: Human motion, environmental contacts, and interaction forces are governed by common physical laws, yet existing approaches typically separate visual pose reconstr…
- arXiv cs.AIresearchGumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps
arXiv:2610.00497v1 Announce Type: cross Abstract: We present Gumbel Straight Flow (GSF), a continuous flow map language model that leverages the noise-data coupling of a pretrained autoregressive language (AR) model. We…
- arXiv cs.AIresearchRules Amortize, Pairings Don't: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning
arXiv:2610.00526v1 Announce Type: cross Abstract: In-context learning (ICL) can be amortized into latent objects (task vectors, function vectors, context vectors) that recover few-shot behavior at zero-shot inference cos…
- arXiv cs.AIresearchRandom Recursive Models
arXiv:2610.00541v1 Announce Type: cross Abstract: Recursive models create computational depth through parameter reuse, offering a parameter-efficient alternative to increasing model size. However, most recursive models r…
- arXiv cs.AIresearchCan LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning
arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient histories. Although…
- arXiv cs.AIresearchBeyond Affine Transformations: A Soft Dominance Layer for Coordinate-Wise Neural Computation
arXiv:2610.00563v1 Announce Type: cross Abstract: This paper presents a preliminary study of an alternative to the affine transformation underlying conventional neural-network layers. In the proposed Soft Dominance Layer…
- arXiv cs.AIresearchEmergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
arXiv:2610.00568v1 Announce Type: cross Abstract: Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between capability and alignmen…
- arXiv cs.AIresearchInterpreting Reasoning of Large Language Models via Partial Information Decomposition
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive, or erroneous reasoni…
- arXiv cs.AIresearchQuery-efficient winner prediction in district-based elections
arXiv:2610.00577v1 Announce Type: cross Abstract: In a district-based election, N voters are partitioned into k districts, and each voter votes for one of m candidates. Each district elects a winner using the plurality r…
- arXiv cs.AIresearchALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning
arXiv:2610.00592v1 Announce Type: cross Abstract: In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next decision. Memory arch…
- arXiv cs.AIresearchWhen Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies
arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for runtime safety thro…
- arXiv cs.AIresearchMIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation
arXiv:2610.00604v1 Announce Type: cross Abstract: Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappears during a task. We…
- arXiv cs.AIresearchWhere's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities
arXiv:2610.00606v1 Announce Type: cross Abstract: Large Language Models increasingly serve as interfaces for knowledge-intensive information seeking tasks across languages by synthesizing multilingual evidence. Prior wor…
- arXiv cs.AIresearchBeyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games
arXiv:2610.00619v1 Announce Type: cross Abstract: In this paper, we extend earlier findings of supra-competitive outcomes in optimal-execution games by identifying a learned punitive mechanism that deters deviations and…
- arXiv cs.AIresearchMisalignment of Low-Loss Regions Causes Grokking
arXiv:2610.00620v1 Announce Type: cross Abstract: Grokking refers to the delayed emergence of validation-set generalization after a model has already overfit the training set. Although first observed in small algorithmic…
- arXiv cs.AIresearchExploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
arXiv:2610.00661v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcem…
- arXiv cs.AIresearchVisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision
arXiv:2610.00666v1 Announce Type: cross Abstract: Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchma…
- arXiv cs.AIresearchClosing the Loop: Practical Training Recipes for Looped Language Models
arXiv:2610.00673v1 Announce Type: cross Abstract: Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage training over trilli…
- arXiv cs.AIresearchLabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
arXiv:2610.00675v1 Announce Type: cross Abstract: Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evi…
- arXiv cs.AIresearchLearning Transferable Skills using Goal-Conditioned Bisimulation
arXiv:2610.00676v1 Announce Type: cross Abstract: Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, current skill discover…
- arXiv cs.AIresearchHow Divergence Becomes Decision Flips in Compressed Language Models
arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outp…
- arXiv cs.AIresearchInitialization Improves LLM-Driven Discovery
arXiv:2610.00707v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks through the use of harnesses that prompt an LLM to iterati…
- arXiv cs.AIresearchSequential Functional Structured Tucker Compression for Large Language Model Attentions
arXiv:2610.00717v1 Announce Type: cross Abstract: Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the…
- arXiv cs.AIresearchOuter Diversity of Condorcet Domains
arXiv:2610.00720v1 Announce Type: cross Abstract: A Condorcet domain is a set of rankings over a given candidate set, such that every election that consists only of (an odd number of) votes from the domain has a transiti…
- arXiv cs.AIresearchBenchmarking Generative Models for Near-Surface Data Assimilation on Real Station Observations
arXiv:2610.00728v2 Announce Type: replace-cross Abstract: Weather reanalysis products rely on computationally intensive numerical weather predictions followed by data assimilation that corrects the forecast toward observ…
- arXiv cs.AIresearchPersonalized Image Generation with Reasoning and Reflection
arXiv:2610.00737v1 Announce Type: cross Abstract: Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, howe…
- arXiv cs.AIresearchIncreasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning
arXiv:2610.00753v1 Announce Type: cross Abstract: End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers of a neural network.…
- arXiv cs.AIresearchPre-training interventions, ex post facto: Grafting model beliefs across checkpoints
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently po…