AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchInteraction Dynamics Modeling and Predictive Control for Safe Steerable Catheter--Tissue Interaction
arXiv:2607.20939v3 Announce Type: replace-cross Abstract: Steerable catheters are the primary tool for cardiac electrophysiology (EP) procedures including radiofrequency ablation, where the tip must be positioned precise…
- arXiv cs.AIresearchWhy Large Language Models and Humans Converge and Diverge in Evaluating Creativity
arXiv:2607.22218v2 Announce Type: replace-cross Abstract: Despite the growing use of large language models (LLMs) as creativity evaluators, evidence of their alignment with human evaluations remains mixed, raising the qu…
- arXiv cs.AIresearchDualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory
arXiv:2607.23614v3 Announce Type: replace-cross Abstract: We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories. The verifier evaluates 't Hooft an…
- arXiv cs.AIresearchPost-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
arXiv:2607.26358v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve performance on a target task while limiting drift from a reference po…
- arXiv cs.AIresearchBudget-Aware LLM Discovery via Cost-Calibrated Frontier Utility
arXiv:2607.26828v4 Announce Type: replace-cross Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adaptive discove…
- arXiv cs.AIresearchSciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
arXiv:2607.27084v3 Announce Type: replace-cross Abstract: Scientific figure quality is bound to the manuscript: a crop can be visually clear and still contradict its caption or the paragraph that cites it. Most image qua…
- arXiv cs.AIresearchRedFlow: Redirect Failure into Action-level Corrections for Flow-matching VLA Policy
arXiv:2607.27782v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) can improve Vision-Language-Action (VLA) policies from deployment experience, but reward- and preference-based RL primarily identifies…
- arXiv cs.AIresearchEfficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
arXiv:2607.28959v2 Announce Type: replace-cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especiall…
- arXiv cs.AIresearchPreferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety
arXiv:2608.02617v2 Announce Type: replace-cross Abstract: We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback fro…
- arXiv cs.AIresearchdots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
arXiv:2608.02673v4 Announce Type: replace-cross Abstract: Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a fle…
- arXiv cs.AIresearchSSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
arXiv:2608.05127v3 Announce Type: replace-cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging. Existing vector quantization method…
- arXiv cs.AIresearchOnce a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration
arXiv:2608.05741v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational misuse, and pl…
- arXiv cs.AIresearchMultivariate Time Series Forecasting needs Cross Variable Loss
arXiv:2608.05742v4 Announce Type: replace-cross Abstract: Multivariate time series forecasting presents unique challenges because future variables often co-evolve under shared system dynamics. While existing studies main…
- arXiv cs.AIresearchFastKron: Efficient Quantization with Kronecker-Factored Hessians
arXiv:2608.06291v2 Announce Type: replace-cross Abstract: We accelerate a family of algorithms for neural network quantization which utilize a two-sided version of the GPTQ/LDLQ algorithm. Standard GPTQ-style adaptive ro…
- arXiv cs.AIresearchTransSLR: A Lightweight Transformer for Sign Language Recognition
arXiv:2608.06407v2 Announce Type: replace-cross Abstract: Automated sign language recognition for underrepresented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this chall…
- arXiv cs.AIresearchMaskFlow: Precise, Consistent and Seamless Regional Image Editing
arXiv:2608.06929v3 Announce Type: replace-cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability. Although instruction-based and mask-based editing methods can achieve…
- arXiv cs.AIresearchEvidence-RL: Towards Evidence-intensive Visual Reasoning
arXiv:2608.08021v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing pe…
- arXiv cs.AIresearchRL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
arXiv:2608.09226v2 Announce Type: replace-cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically…
- arXiv cs.AIresearchError-Aware Reverse Auction Mechanism for Large Language Model Routing
arXiv:2608.12719v2 Announce Type: replace-cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center t…
- arXiv cs.AIresearchSpectral Saliency for Machine Unlearning
arXiv:2608.15548v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inver…
- arXiv cs.AIresearchMultinomial Subset Routing with Sum-Max Rewards and Operational Constraints
arXiv:2608.16375v2 Announce Type: replace-cross Abstract: We study online routing to subsets of experts under aggregate bandit feedback and long-run operational constraints. Expert contributions can be complementary: for…
- arXiv cs.AIresearchPTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX
arXiv:2608.17379v3 Announce Type: replace-cross Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench…
- arXiv cs.AIresearchPartition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
arXiv:2608.18484v2 Announce Type: replace-cross Abstract: Block-sparse attention accelerates video transformers by grouping queries and keys and computing attention only between selected groups. However, it faces two cha…
- arXiv cs.AIresearchIn Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
arXiv:2608.19514v2 Announce Type: replace-cross Abstract: Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared…
- arXiv cs.AIresearchThe Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
arXiv:2608.22876v3 Announce Type: replace-cross Abstract: Hybrid sequence models must satisfy prefix invariance: representations at position t must not depend on future inputs, yet this is rarely verified. We formalize p…
- arXiv cs.AIresearchPhysics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography
arXiv:2608.23562v2 Announce Type: replace-cross Abstract: Ballistocardiography (BCG) is promising for unobtrusive long-term blood pressure (BP) monitoring in laboratory settings, but traditional BCG signals are vulnerabl…
- arXiv cs.AIresearchLuce: Relightable Gaussians for 3D Asset Generation
arXiv:2608.23943v2 Announce Type: replace-cross Abstract: High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. However, preserving fine detail across the physicall…
- arXiv cs.AIresearchFRAME: Separating sampling variation from performance disparities in medical image analysis
arXiv:2608.25981v2 Announce Type: replace-cross Abstract: Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidenc…
- arXiv cs.AIresearchFlow-JEPA: Robust Latent Dynamics for JEPA World Models via Flow Matching
arXiv:2608.29029v3 Announce Type: replace-cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) provide a powerful framework for latent world modeling and planning in a reconstruction-free manner. Although num…
- arXiv cs.AIresearchHistory-Conditioned Joint-Prefix Alignment for Generative Recommendation
arXiv:2608.29179v2 Announce Type: replace-cross Abstract: Generative recommendation retrieves items by autoregressively generating semantic identifiers, but beam search may discard a target before its complete identifier…
- arXiv cs.AIresearchPokaiTrainer: Scaling Equilibrium Search to Competitive Pok\'emon VGC
arXiv:2608.29197v2 Announce Type: replace-cross Abstract: Decision-time equilibrium search carried poker to superhuman play, but it has so far relied on tractable subgames: a handful of actions per decision, chance confi…
- arXiv cs.AIresearchEEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction
arXiv:2609.00653v2 Announce Type: replace-cross Abstract: Electroencephalography (EEG) is a non-invasive technique for measuring neural activity and has been widely used in neuroscience applications. Recent advances in E…
- arXiv cs.AIresearchHiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
arXiv:2609.01282v2 Announce Type: replace-cross Abstract: Vision Transformer (ViT) design has become increasingly diverse, with backbones combining convolutional stems, windowed, linear, or multi-axis attention, patch me…
- arXiv cs.AIresearchLinear Reusable Neural Bases Architecture for Network Compression
arXiv:2609.01550v3 Announce Type: replace-cross Abstract: Memory constraints remain a critical bottleneck in the deployment of large-scale AI models. Parameter sharing across network depth reduces model storage, but repe…
- arXiv cs.AIresearchPercolation Dynamics in Optimization: Variance Cascades and Nested Symmetry
arXiv:2609.02373v2 Announce Type: replace-cross Abstract: We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetwo…
- arXiv cs.AIresearchContinual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI
arXiv:2609.04552v2 Announce Type: replace-cross Abstract: Unattended interactive autonomy - machines that step into danger in place of humans and complete tasks with human tools - remains a missing capability in mission-…
- arXiv cs.AIresearchBetter Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
arXiv:2609.04909v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limite…
- arXiv cs.AIresearchTabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables
arXiv:2609.07441v2 Announce Type: replace-cross Abstract: Biomedical tables often combine thousands of measured variables with only tens or hundreds of labelled samples, a regime that is poorly represented in general-pur…
- arXiv cs.AIresearchBeyond the Matrix Sign: Quadratic Spectral Descent
arXiv:2609.07597v2 Announce Type: replace-cross Abstract: Muon emerges as a strong competitor of the AdamW for LLM pretraining, because the matrix-wise update it employs can potentially incur smaller second-order penalty…
- arXiv cs.AIresearchKBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
arXiv:2609.08135v2 Announce Type: replace-cross Abstract: We develop a second-order theory of quantization noise in matrix multiplication in which the quantization format is characterized by the variance it assigns to ea…
- arXiv cs.AIresearchIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Post-Retrieval Context Tampering
arXiv:2609.09243v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved t…
- arXiv cs.AIresearchBreak Step: Recursive Training Resonates with Replayed Sampling Noise
arXiv:2609.11149v3 Announce Type: replace-cross Abstract: How fast does a language model degrade when trained on its own outputs? Theory traces it to gradually accumulating errors, while experiments report repeated phras…
- arXiv cs.AIresearchSolving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer
arXiv:2609.11228v2 Announce Type: replace-cross Abstract: Applying knowledge transfer across multiple optimization tasks, multitask optimization (MTO) emerges as a promising approach to solving synergistic optimization t…
- arXiv cs.AIresearchA latent dimension of Condorcet's jury theorem for multiple AI advisers
arXiv:2609.14438v2 Announce Type: replace-cross Abstract: When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that adding independe…
- arXiv cs.AIresearchWaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians
arXiv:2609.14706v2 Announce Type: replace-cross Abstract: How should a Kronecker-factored Hessian approximation be chosen for post-training quantization? We address this question through WaterKron, which combines two-sid…
- arXiv cs.AIresearchSpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy
arXiv:2609.15039v3 Announce Type: replace-cross Abstract: User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution en…
- arXiv cs.AIresearchRefinement-Based Flow Policy Optimization
arXiv:2609.15123v2 Announce Type: replace-cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from the distribut…
- arXiv cs.AIresearchEvaluating Losslessness in Speculative Decoding Under Finite-Precision Inference
arXiv:2609.15504v2 Announce Type: replace-cross Abstract: Lossless speculative decoding is typically defined at the algorithmic level: a speculative procedure proposes multiple tokens and a verification procedure is desi…
- arXiv cs.AIresearchK-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
arXiv:2609.15855v3 Announce Type: replace-cross Abstract: People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised…
- Apple Machine Learning ResearchresearchThe Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survives this bottleneck? W…