AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMitigating Reward Hacking in Realistic Scenarios Through Representation Engineering
arXiv:2610.29129v1 Announce Type: cross Abstract: Reward hacking is a major problem in current production machine learning systems, resulting in costly and dangerous failures. Here we study how to monitor for and mitigat…
- arXiv cs.AIresearchGRAFT: Restoring the Missing Sampling Interface in Continuous Diffusion Language Models
arXiv:2610.29136v1 Announce Type: cross Abstract: Continuous diffusion language models generate a whole sequence in parallel, never drawing a single word at any intermediate step; only the final step turns embeddings int…
- arXiv cs.AIresearchFrom AI-Free Gates to AI-First Work: How Engineering Students in India Navigate University Education and Career Preparation Without AI Guidelines
arXiv:2610.29140v2 Announce Type: replace-cross Abstract: Engineering graduates in India enter a technology sector that is being reshaped by generative AI, yet the route into that sector runs through examinations and cam…
- arXiv cs.AIresearchORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization
arXiv:2610.29145v1 Announce Type: cross Abstract: Large language models increasingly automate optimization modeling from natural language problems, producing written mathematics, solver code and a returned report. Verify…
- arXiv cs.AIresearchWhere Does Timbre Hide? Localizing Speaker Information in Speech Signals
arXiv:2610.29150v1 Announce Type: cross Abstract: Timbre similarity is a key evaluation target for generative speech systems, including voice conversion, speaker-cloning text-to-speech, and zero-shot speech models. When…
- arXiv cs.AIresearchFrom Augmentation to Synthetic Evidence: Evaluating Generated Chest Radiographs at Dataset Intake
arXiv:2610.29152v1 Announce Type: cross Abstract: A generated chest radiograph can be useful as declared augmentation, but the same image becomes unsupported evidence when submitted as the record of a real examination. W…
- arXiv cs.AIresearchAI-Based End-to-End Automotive Design and Software Development for SDVs
arXiv:2610.29160v1 Announce Type: cross Abstract: This paper explores the potential of Artificial Intelligence (AI) to enable end-to-end automotive design and software development for Software-Defined Vehicles (SDVs). Ba…
- arXiv cs.AIresearchWhy is AI-generated language so hard to understand?
arXiv:2610.29162v1 Announce Type: cross Abstract: There is a widespread sense that AI-generated text has recently become harder to understand. In this study, we investigate a set of psycholinguistic features that are kno…
- arXiv cs.AIresearchHow Representational Priors Shape Generalization in World Action Models
arXiv:2610.29168v1 Announce Type: cross Abstract: World action models (WAMs) are shown to substantially diverge under generalization performance based on their generative backbones. We investigate this gap through the re…
- arXiv cs.AIresearchConditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance
arXiv:2610.29172v1 Announce Type: cross Abstract: Conditional Flow Models (CFMs) are increasingly being used in place of deterministic predictors across machine learning, including for tasks that were classically formula…
- arXiv cs.AIresearchResuming Vision-Language Inference across Onboard Interruptions
arXiv:2610.29183v1 Announce Type: cross Abstract: Executing vision-language models (VLMs) aboard low-Earth orbit satellites enables flexible processing of observation data without first downlinking it to the ground. On c…
- arXiv cs.AIresearchLTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation
arXiv:2610.29188v2 Announce Type: replace-cross Abstract: Tables in real-world documents, including scientific papers, financial reports, and statistical summaries, frequently use merged cells, multi-level headers, and s…
- arXiv cs.AIresearchHuayu-Global: Skillful real-time quasi-global precipitation retrieval
arXiv:2610.29213v1 Announce Type: cross Abstract: Satellite precipitation products face a persistent trade-off: real-time estimates are timely but less accurate, whereas the most reliable products are often released mont…
- arXiv cs.AIresearchBeyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics
arXiv:2610.29225v1 Announce Type: cross Abstract: Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and suffering from low consistency across automated judges. To…
- arXiv cs.AIresearchHierarchical Masked Diffusion Language Models
arXiv:2610.29255v1 Announce Type: cross Abstract: Masked diffusion language models have emerged as an alternative to autoregressive models, enabling parallel token generation. However, standard masked diffusion language…
- arXiv cs.AIresearchCRAB: Cuboid-based Representation for As-built BIM from Point Clouds
arXiv:2610.29257v1 Announce Type: cross Abstract: As-built BIM reconstruction from point clouds demands semantic, volumetric, parametric, and editable building components, beyond 2D layouts or planar abstractions. Yet ex…
- arXiv cs.AIresearchFlat-RLVR: Sharpness-Aware Reinforcement Learning with Verifiable Rewards for Reasoning Capacity in LLMs
arXiv:2610.29281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR), particularly through group-relative policy optimization (GRPO), has emerged as a central paradigm for the post-trai…
- arXiv cs.AIresearchLatent space configuration for neural network finetuning, fast ranking, and embedding dimensionality reduction
arXiv:2610.29295v2 Announce Type: replace-cross Abstract: Finding K most similar elements for a query in a large gallery of neural network (NN) embeddings is essential in various areas of computer science and industrial…
- arXiv cs.AIresearchWhen Are We Near Nash? Certifying Solutions in General-Sum Games
arXiv:2610.29300v1 Announce Type: cross Abstract: Heuristic solvers for general-sum extensive-form games produce a stream of iterates, and practice reports the NashGap of the returned profile. We ask what a solver can kn…
- arXiv cs.AIresearchYingLan: A Multimodal Ocean Foundation Model for Unified Representation Learning from Heterogeneous Observations
arXiv:2610.29313v1 Announce Type: cross Abstract: Multimodal ocean modeling remains challenging due to substantial heterogeneity in data structures, physical semantics, and spatiotemporal characteristics across satellite…
- arXiv cs.AIresearchOpenMAP-HIE: Pathology Informed Score-based Diffusion Model for Unsupervised Neonatal Hypoxic-Ischemic Encephalopathy Lesion Segmentation
arXiv:2610.29322v2 Announce Type: replace-cross Abstract: Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is lim…
- arXiv cs.AIresearchChronoSynth: Constraint-Aware Question Synthesis over Temporal Knowledge Graphs
arXiv:2610.29339v1 Announce Type: cross Abstract: Knowledge graph question generation (KGQG) generates natural-language questions from structured graph evidence and a target answer. When the input graph is temporal, a va…
- arXiv cs.AIresearchReading the Mask: Descriptor-Grounded BI-RADS Rationale Generation for Breast MRI Segmentation
arXiv:2610.29358v1 Announce Type: cross Abstract: Deep learning based models accurately delineate tumours on dynamic contrast-enhanced MRI (DCE-MRI), but segmentation masks alone do not provide the rationales or reasonin…
- arXiv cs.AIresearchParallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories
arXiv:2610.29385v2 Announce Type: replace-cross Abstract: Language models relying on verbalized Chain-of-Thought (CoT) are constrained to token-by-token generation in the language space, where many tokens serve textual c…
- arXiv cs.AIresearchLLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines
arXiv:2610.29409v1 Announce Type: cross Abstract: Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require dedicated architectures, large-scale annotation engines, and task-…
- arXiv cs.AIresearchOmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling
arXiv:2610.29472v1 Announce Type: cross Abstract: Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-…
- arXiv cs.AIresearchGenerative Modeling via Nonlinear Schr\"odinger Bridges and Branching Diffusions
arXiv:2610.29476v1 Announce Type: cross Abstract: We propose a new generative modeling framework grounded in forward-backward partial differential equations (PDEs). These equations arise naturally in mean-field game (MFG…
- arXiv cs.AIresearchA Strong MoE Is All You Need for Process Supervision
arXiv:2610.29498v1 Announce Type: cross Abstract: Process reward models (PRMs) provide fine-grained supervision for multi-step reasoning, yet obtaining reliable process labels remains a central bottleneck. Existing appro…
- arXiv cs.AIresearchKeeping Time vs. Understanding Time: Neither Alone Explains Temporal Reasoning in LLMs
arXiv:2610.29507v1 Announce Type: cross Abstract: Temporal reasoning is widely assumed to decompose into two modes: temporal arithmetic (date and time calculations), and temporal semantics (understanding temporal and cau…
- arXiv cs.AIresearchMitigating Query Shortcuts in Chain-of-Thought with Context-Aware Decoding
arXiv:2610.29518v1 Announce Type: cross Abstract: While Chain-of-Thought (CoT) prompting improves the reasoning performance of large language models (LLMs), recent studies have shown that final answers do not always depe…
- arXiv cs.AIresearchAre Joint-Embedding Predictive Objectives Effective for Longitudinal EHRs?
arXiv:2610.29528v1 Announce Type: cross Abstract: Masked language modelling (MLM) is the dominant pretraining objective for transformer encoders applied to longitudinal electronic health records (EHRs). However, reconstr…
- arXiv cs.AIresearchBlock Diffusion for Longitudinal EHR: Accuracy, Efficiency, and Representation Trade-offs
arXiv:2610.29533v1 Announce Type: cross Abstract: Autoregressive (AR) models have proved effective for zero-shot prediction from longitudinal electronic health records, but impose strictly sequential generation on trajec…
- arXiv cs.AIresearchStochastic Pruning of the DPO Computation Graph: 1.4x Faster Training and Lower Peak Memory
arXiv:2610.29538v1 Announce Type: cross Abstract: Direct preference optimization (DPO) incurs training costs in output scoring, sequence execution, and backpropagation, so reducing supervision alone does not necessarily…
- arXiv cs.AIresearchImproved Training of Strong Stochastic Flow Maps
arXiv:2610.29605v1 Announce Type: cross Abstract: Stochastic flow maps promise few-step sampling of stochastic differential equations (SDEs) by learning to directly jump between times along the solution path, yet trainin…
- arXiv cs.AIresearchOverview of CHIP 2026 Shared Task 1: Patient-Specific Phenotype Concept Recognition in Full-Text Biomedical Literature
arXiv:2610.29606v2 Announce Type: replace-cross Abstract: Automatic phenotype information extraction plays an important role in rare disease diagnosis, genotype-phenotype analysis, and precision medicine. However, accura…
- arXiv cs.AIresearchAn interpretable deep learning method for early hepatocellular carcinoma diagnosis on multiphase CT
arXiv:2610.29616v1 Announce Type: cross Abstract: Early diagnosis of hepatocellular carcinoma is critical to preserve access to curative treatment options. The Liver Imaging Reporting and Data System (LI-RADS) provides a…
- arXiv cs.AIresearchFormalizing Cooperation and Competition: An AI-Assisted Mathematical Addendum to a 2018 Planning Thesis
arXiv:2610.29637v1 Announce Type: cross Abstract: We present an AI-assisted mathematical addendum to Strategic Trip Planning: Striking a Balance Between Competition and Cooperation (Amar, 2018). We reconstruct selected r…
- arXiv cs.AIresearchLineage-Aware Search Control for LLM-Based Evolutionary Factor Mining
arXiv:2610.29663v1 Announce Type: cross Abstract: Formulaic alpha factor mining searches for symbolic expressions that transform market data into predictive signals. Recent LLM-based evolutionary factor mining methods us…
- arXiv cs.AIresearchConflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement
arXiv:2610.29669v1 Announce Type: cross Abstract: LLM-generated records increasingly populate production information systems where they are treated as data assets subject to the same quality expectations as records from…
- arXiv cs.AIresearchScaling Multilingual Pretraining of Pixel Language Models
arXiv:2610.29681v1 Announce Type: cross Abstract: Pixel language models process text as rendered images instead of a finite vocabulary, which gives them strong cross-lingual transfer abilities. However, not much is known…
- arXiv cs.AIresearchBio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition
arXiv:2610.29720v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) promise energy-efficient inference through sparse, event-driven computation, yet remain constrained on continuous, context-dependen…
- arXiv cs.AIresearchStructure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion
arXiv:2610.29725v1 Announce Type: cross Abstract: A common application of the process mining discipline is to connect observed event data with Petri nets, which are bipartite, directed graphical process models with rich…
- arXiv cs.AIresearchSAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones
arXiv:2610.29733v1 Announce Type: cross Abstract: Diffusion transformers are widely used in image-editing services. To preserve both efficiency and privacy, existing systems commonly rely on cloud-device collaboration. K…
- arXiv cs.AIresearchMetamodel-Guided LLM Decoding for Consistent DSL Generation
arXiv:2610.29749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually m…
- arXiv cs.AIresearchWhere Do LLMs Learn to Recommend AI?
arXiv:2610.29785v1 Announce Type: cross Abstract: Asked what to study, which career to pursue, or what product to build, large language models (LLMs) often recommend AI-related options. We ask where this tendency comes f…
- arXiv cs.AIresearchRobot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities
arXiv:2610.29829v2 Announce Type: replace-cross Abstract: General-purpose robots must handle tasks, objects and environments they were never trained on, yet zero-shot generalization remains one of the least solved proble…
- arXiv cs.AIresearchS-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs
arXiv:2610.29832v1 Announce Type: cross Abstract: Calibrating large language models (LLMs) in open-ended generation is uniquely challenging because many distinct token sequences can express the same underlying meaning. P…
- arXiv cs.AIresearchBroadband Mid-Wave Infrared Imaging Enabled by All-Silicon Hyperboloid Metalens
arXiv:2610.29841v1 Announce Type: cross Abstract: The mid-wave infrared (MWIR, 3-5 microns) is indispensable for thermal sensing, gas detection, long-range imaging, and free-space optical communications. Meta-optics offe…
- arXiv cs.AIresearchEvery Part Has Its Role: Part-of-Speech Effects in LLM Post-Training
arXiv:2610.29843v1 Announce Type: cross Abstract: Large language models are typically trained with next-token prediction (NTP), which rewards predicting specific tokens rather than explicitly accounting for the semantic…
- arXiv cs.AIresearchAutomated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
arXiv:2610.29895v1 Announce Type: cross Abstract: Over the past decade, substantial efforts have been devoted to developing machine learning (ML) methods for extracting materials data and, where possible, materials knowl…