AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchValidity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
arXiv:2610.10506v1 Announce Type: new Abstract: Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh comp…
- arXiv cs.AIresearchRECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
arXiv:2610.10507v1 Announce Type: new Abstract: Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fix…
- arXiv cs.AIresearchRoboJEPA: Scaling Robotic Latent World Models
arXiv:2610.10515v1 Announce Type: new Abstract: Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how t…
- arXiv cs.AIresearchTokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages
arXiv:2610.08794v1 Announce Type: cross Abstract: Large language models rely on subword tokenizers whose quality varies across languages, yet no standardized multi-metric framework exists for broad comparative evaluation…
- arXiv cs.AIresearchBeyond Baseline Severity: Temporal and Disease-Specific Predictors of Depression Outcomes Following Mindfulness Interventions
arXiv:2610.08809v1 Announce Type: cross Abstract: Depression severity among patients with chronic or acute medical conditions is influenced by a complex interaction of baseline psychological state, demographic characteri…
- arXiv cs.AIresearchTransferability and operational reliability of a Prithvi crop classification foundation model under phenological and geographic shift across three continents
arXiv:2610.08810v1 Announce Type: cross Abstract: Fine-tuned geospatial foundation models (GeoFMs) pretrained on large satellite archives have been shown to improve crop classification accuracy and geographic transferabi…
- arXiv cs.AIresearchKVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression
arXiv:2610.08811v1 Announce Type: cross Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing methods fall into thr…
- arXiv cs.AIresearchPre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset
arXiv:2610.08813v1 Announce Type: cross Abstract: X-ray image-based Radiology Report Generation (RRG) constitutes a critical research direction within medical artificial intelligence, with great potential to alleviate cl…
- arXiv cs.AIresearchJust for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
arXiv:2610.08818v2 Announce Type: replace-cross Abstract: Spatio-temporal forecasting is a cornerstone of logistics, urban planning, and intelligent transportation systems. However, constrained by deployment costs and ma…
- arXiv cs.AIresearchHydroSphere: A Framework for Governed, Self-Healing Wastewater Infrastructure
arXiv:2610.08819v1 Announce Type: cross Abstract: Rapid industrialization and urban growth are increasing pressure on water quality and wastewater treatment systems, while conventional treatment plants often rely on stat…
- arXiv cs.AIresearchChild ASR Adaptation with Adult Retention: An Empirical Study
arXiv:2610.08827v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems often underperform for children and non-native speakers, while adapting adult ASR models to child speech can cause adult-speech…
- arXiv cs.AIresearchJoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation
arXiv:2610.08834v1 Announce Type: cross Abstract: We present JoyAI-Voice~2.0, an end-to-end anthropomorphic speech generation model built upon a fully continuous, dual-encoder architecture. Raw speech is encoded into con…
- arXiv cs.AIresearchLeveraging LLM-Generated Explanations for Detecting Emotionally Rewritten Fake News
arXiv:2610.08835v2 Announce Type: replace-cross Abstract: The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate external in…
- arXiv cs.AIresearchDeep Learning for Longitudinal Medical Imaging: A Scoping Review
arXiv:2610.08838v1 Announce Type: cross Abstract: Longitudinal medical imaging analysis is a cornerstone of modern medical practice and patient care. Deep learning applied to longitudinal imaging offers wide potential to…
- arXiv cs.AIresearchBeyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding
arXiv:2610.08840v1 Announce Type: cross Abstract: Large language models (LLMs) often abandon a correct answer, or endorse a user's position, once the user pushes back. This behavior, called sycophancy, is usually reporte…
- arXiv cs.AIresearchBeyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment
arXiv:2610.08842v1 Announce Type: cross Abstract: Identifying suicide risk from social networking services (SNS) posts is important for detecting suicide-related signals in online environments. However, risk classificati…
- arXiv cs.AIresearchSTRIDE: Spatial-Temporal Representation for Interval-conditioned Disease Evolution in Longitudinal Glioblastoma MRI
arXiv:2610.08848v1 Announce Type: cross Abstract: Glioblastoma (GBM), an aggressive primary brain tumor, is routinely monitored with longitudinal MRI after treatment. Distinguishing stable disease (SD), pseudoprogression…
- arXiv cs.AIresearchQuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance
arXiv:2610.08851v1 Announce Type: cross Abstract: Quantifying language distance among closely related languages remains a core challenge in quantitative linguistics. Our previous work [1] introduced QuanLing (Quantitativ…
- arXiv cs.AIresearchLRCC: Generalizing Low-Rank Compression with Conditional Computation
arXiv:2610.08858v1 Announce Type: cross Abstract: Low-rank compression reduces the cost of pretrained language models by replacing linear transformations with low-rank factorizations. However, conventional methods use a…
- arXiv cs.AIresearchTiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies
arXiv:2610.08879v1 Announce Type: cross Abstract: Pretraining strategies significantly impact the quality of language models, yet existing comparisons of Masked Language Modeling (MLM), Whole Word Masking (WWM), and MacB…
- arXiv cs.AIresearchPhysics-based Sphere Packing for Lagrangian Mesh Morphing
arXiv:2610.08880v1 Announce Type: cross Abstract: This paper studies tetrahedral meshes as the body representation for differentiable simulation and computational design. Fixed-connectivity meshes degrade under large mor…
- arXiv cs.AIresearchFinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks
arXiv:2610.08882v1 Announce Type: cross Abstract: FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapted models on the sam…
- arXiv cs.AIresearchHybrid++: The Bridge between PDE Models and Deep Learning for Gamma Noise Removal
arXiv:2610.08892v1 Announce Type: cross Abstract: Multiplicative gamma noise is one of the dominant noise factors in Synthetic Aperture Radar (SAR) and medical ultrasound images. They are dependent on pixel level noises…
- arXiv cs.AIresearchTrustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
arXiv:2610.08894v1 Announce Type: cross Abstract: This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning. It integrate…
- arXiv cs.AIresearchContextualization of Third-Party Cloud Security Findings
arXiv:2610.08895v1 Announce Type: cross Abstract: Finding severity is the main driver of how security teams prioritize remediation. For third-party cloud security findings, that severity is static: the rule that raised t…
- arXiv cs.AIresearchA Shortcut to Structure in AlphaFold 3
arXiv:2610.08937v1 Announce Type: cross Abstract: AlphaFold 3 predicts protein structures with remarkable accuracy, yet how structural information emerges within the model remains poorly understood. Here, through causal…
- arXiv cs.AIresearchOne-Slide Calibration of Pathology Foundation Models
arXiv:2610.08944v2 Announce Type: replace-cross Abstract: Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses other regions within a slide as internal…
- arXiv cs.AIresearchWork While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
arXiv:2610.08969v2 Announce Type: replace-cross Abstract: Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two co…
- arXiv cs.AIresearchLASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL
arXiv:2610.08989v2 Announce Type: replace-cross Abstract: While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk…
- arXiv cs.AIresearchPhysEvo: Astra Can Act, Let It
arXiv:2610.08995v1 Announce Type: cross Abstract: Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive…
- arXiv cs.AIresearchAlgorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers
arXiv:2610.09003v1 Announce Type: cross Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and long division. In t…
- arXiv cs.AIresearchPersonalize at Test Time: Learning User Preferences for Image Generation
arXiv:2610.09015v1 Announce Type: cross Abstract: Diffusion models can generate high-quality images, yet aligning their outputs with individual user preferences remains challenging. A key bottleneck is accurately modelin…
- arXiv cs.AIresearchQuad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
arXiv:2610.09033v1 Announce Type: cross Abstract: Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment routinely receive inpu…
- arXiv cs.AIresearchCareful Judge: Safe and Efficient Human-AI Collaborative Decision Making
arXiv:2610.09043v1 Announce Type: cross Abstract: In human-AI collaborative decision making, human review can prevent unsafe AI decisions, but each human judgment is costly. Treating human intervention after AI abstentio…
- arXiv cs.AIresearchMimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking
arXiv:2610.09055v1 Announce Type: cross Abstract: Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. The…
- arXiv cs.AIresearchTalking with Language Models
arXiv:2610.09064v1 Announce Type: cross Abstract: When we interact with large language models (LLMs), are we having a conversation? They are designed to invite us to treat them as intelligent interlocutors who remember,…
- arXiv cs.AIresearchU-Space: Uncovering When and Why Uncertainty Arises in Language Models
arXiv:2610.09087v1 Announce Type: cross Abstract: Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can…
- arXiv cs.AIresearchMaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
arXiv:2610.09092v3 Announce Type: replace-cross Abstract: State Space Models (SSMs) offer an efficient alternative to Transformers for sequence modeling, yet conditioning pre-trained SSMs for iterative generation typical…
- arXiv cs.AIresearchConvex-Concave Reinforcement Learning
arXiv:2610.09108v1 Announce Type: cross Abstract: Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (ma…
- arXiv cs.AIresearchSpatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata
arXiv:2610.09124v1 Announce Type: cross Abstract: Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant to a prediction for…
- arXiv cs.AIresearchsk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak
arXiv:2610.09152v1 Announce Type: cross Abstract: Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-benc…
- arXiv cs.AIresearchLower Bounds for Parallel Diffusion Sampling
arXiv:2610.09166v1 Announce Type: cross Abstract: Standard diffusion samplers generate samples through repeated evaluations of a learned score function. Parallel sampling methods seek to accelerate generation by trading…
- arXiv cs.AIresearchLayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition
arXiv:2610.09179v1 Announce Type: cross Abstract: As data propagates through a Transformer, the norm of its hidden states grows by orders of magnitude with depth, a phenomenon framed as 'curse of depth' and nearly univer…
- arXiv cs.AIresearchPatient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?
arXiv:2610.09194v1 Announce Type: cross Abstract: Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A populati…
- arXiv cs.AIresearchDo Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency
arXiv:2610.09205v1 Announce Type: cross Abstract: Modern image editing models can satisfy a text instruction while breaking the physics of the edited scene. A new object may cast no shadow, a mirror may fail to reflect v…
- arXiv cs.AIresearchMulti-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation
arXiv:2610.09209v1 Announce Type: cross Abstract: Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and readiness for change.…
- arXiv cs.AIresearchCurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search
arXiv:2610.09212v1 Announce Type: cross Abstract: The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, which must be undone a…
- arXiv cs.AIresearchA Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video
arXiv:2610.09217v1 Announce Type: cross Abstract: Autism spectrum disorder (ASD) is diagnosed through specialist observation of a child's social behavior, and access to that expertise is the bottleneck for early identifi…
- arXiv cs.AIresearchConsistent Distribution Matching for Data-Free Diffusion Distillation
arXiv:2610.09221v1 Announce Type: cross Abstract: Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to…
- arXiv cs.AIresearchConditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions
arXiv:2610.09229v1 Announce Type: cross Abstract: LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate view hides the de…