AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchA Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese
arXiv:2610.04898v2 Announce Type: replace-cross Abstract: This study analyzes the predictive power of LM-derived, token-level surprisal on Mandarin Chinese reading times. We first propose the Shortest Matching Sequence (…
- arXiv cs.AIresearchScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
arXiv:2610.04905v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are a central tool in mechanistic interpretability. However, existing SAEs are primarily trained per layer. The modeling subspace is therefore…
- arXiv cs.AIresearchWhy Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery
arXiv:2610.04907v1 Announce Type: cross Abstract: Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands…
- arXiv cs.AIresearchTSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models
arXiv:2610.04925v1 Announce Type: cross Abstract: Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is e…
- arXiv cs.AIresearchDiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
arXiv:2610.04933v2 Announce Type: replace-cross Abstract: Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Ve…
- arXiv cs.AIresearchD-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
arXiv:2610.04938v2 Announce Type: replace-cross Abstract: We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models with gener…
- arXiv cs.AIresearchA Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs
arXiv:2610.04939v1 Announce Type: cross Abstract: We ask whether physically meaningful correspondences discovered inside a trained scientific model remain meaningful outside the conditions under which they were discovere…
- arXiv cs.AIresearchTempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions
arXiv:2610.04945v2 Announce Type: replace-cross Abstract: Destructive single-cell measurements provide unpaired population snapshots rather than observations of the same cells across conditions. Local cell states and tra…
- arXiv cs.AIresearchA Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim
arXiv:2610.04949v1 Announce Type: cross Abstract: Reinforcement learning controllers for underwater vehicles are usually trained against one physics representation and deployed against another, so reported performance do…
- arXiv cs.AIresearchEDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
arXiv:2610.04953v2 Announce Type: replace-cross Abstract: Euclidean combinatorial optimization problems (ECOPs), such as the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP), possess inhere…
- arXiv cs.AIresearchKapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery
arXiv:2610.04955v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) radar enables unobtrusive, contactless electrocardiogram (ECG) reconstruction for cardiac monitoring. Time-frequency spectrograms preserve fine c…
- arXiv cs.AIresearchTeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry
arXiv:2610.04981v1 Announce Type: cross Abstract: Large language models can generate runnable web applications from natural-language requirements, but many generated applications still fail interactive tasks. Existing ge…
- arXiv cs.AIresearchHidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
arXiv:2610.04985v1 Announce Type: cross Abstract: Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this…
- arXiv cs.AIresearchOperational Abstractions of Neural Network Concepts via Topological Representations
arXiv:2610.05017v1 Announce Type: cross Abstract: Concept-based methods provide a semantic level for interpreting and manipulating learned representations, but existing editing approaches are typically specialized to par…
- arXiv cs.AIresearchCommunication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia
arXiv:2610.05041v1 Announce Type: cross Abstract: When does communication help a group identify hidden adversaries, and how does its value change as the group adapts? In Mafia, an informed minority hides inside an uninfo…
- arXiv cs.AIresearchAraYoungVoices: A Diverse L1/L2 Corpus of Arabic Child and Adolescent Speech
arXiv:2610.05044v1 Announce Type: cross Abstract: State-of-the-art ASR systems primarily target native adult speech, leading to substantial performance gaps for children, adolescents, and L2 speakers. We introduce AraYou…
- arXiv cs.AIresearchE$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation
arXiv:2610.05048v5 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) provides dense token-level supervision without a second model: one network acts as teacher with the reference solution and as s…
- arXiv cs.AIresearchLogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
arXiv:2610.05051v1 Announce Type: cross Abstract: Time-series data are often sampled irregularly at high frequencies and exhibit long-range dependencies, which makes long-horizon modelling difficult. Continuous-time mode…
- arXiv cs.AIresearchDiscrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs
arXiv:2610.05071v1 Announce Type: cross Abstract: Learning population dynamics from unpaired temporal marginals is an ill-posed inverse problem that requires structural assumptions on the underlying dynamics. We introduc…
- arXiv cs.AIresearchSelf-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation
arXiv:2610.05076v1 Announce Type: cross Abstract: Test-time training (TTT) lets a model store information in its weights during inference. When the model learns from its own output, however, each update also changes the…
- arXiv cs.AIresearchTracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech
arXiv:2610.05080v1 Announce Type: cross Abstract: LLM-based text-to-speech (TTS) models can generate emotionally expressive speech, but how reference emotion is routed through the model and realized in decoded speech rem…
- arXiv cs.AIresearchDirection-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning
arXiv:2610.05087v1 Announce Type: cross Abstract: Contrastive Reinforcement Learning (CRL) learns representations that estimate goal reachability, yet its policy remains conditioned on raw goals and therefore does not di…
- arXiv cs.AIresearchReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory
arXiv:2610.05097v1 Announce Type: cross Abstract: As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memory reintroduces vi…
- arXiv cs.AIresearchVulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence
arXiv:2610.05103v1 Announce Type: cross Abstract: Reliable learning-based vulnerability detection requires high-quality labels, yet datasets built from vulnerability-fixing commits may label functions as vulnerable simpl…
- arXiv cs.AIresearchBest-of-$N$ Guidance for Test-time Diffusion Alignment
arXiv:2610.05108v2 Announce Type: replace-cross Abstract: Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple y…
- arXiv cs.AIresearchBayesian Entropy-based Reordering for Calibrated Diffusion Language Models
arXiv:2610.05125v1 Announce Type: cross Abstract: Masked Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked tokens with model predictions. At each denoising step, the decoder chooses whi…
- arXiv cs.AIresearchHow Does Geometry Enter Generated Motion?
arXiv:2610.05135v1 Announce Type: cross Abstract: Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We fix the law and t…
- arXiv cs.AIresearchCross-Modal Contrastive Learning for the Retrieval of Immunotherapy-Associated Molecular Signatures from Histopathology
arXiv:2610.05157v1 Announce Type: cross Abstract: Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their ident…
- arXiv cs.AIresearchSame Predictions, Different Harms: Causal Auditing of Patient World Models
arXiv:2610.05198v1 Announce Type: cross Abstract: Patient world models used for clinical trial simulation can agree on transition kernels and arm-specific risks, yet disagree on the fraction of patients harmed by switchi…
- arXiv cs.AIresearchVela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
arXiv:2610.05230v1 Announce Type: cross Abstract: Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This po…
- arXiv cs.AIresearchEMG-GPT: Predictive Pretraining on Residual-Quantized EMG Tokens for Hand Pose Estimation
arXiv:2610.05235v1 Announce Type: cross Abstract: Surface electromyography (sEMG) is a low-power, cost-effective biosignal for hand-pose estimation and gesture classification. In this work, we examine whether self-superv…
- arXiv cs.AIresearchPythia: Toward Foundation World Models for Multimodal Time Series
arXiv:2610.05240v1 Announce Type: cross Abstract: Time-series foundation models offer a unified approach to forecasting across heterogeneous domains. Textual context and auxiliary observations provide complementary infor…
- arXiv cs.AIresearchMGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation
arXiv:2610.05252v1 Announce Type: cross Abstract: Diffusion-based dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven diffusion models prioritize density approximation over the disc…
- arXiv cs.AIresearchTask-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection
arXiv:2610.05264v1 Announce Type: cross Abstract: Advances in speech synthesis have made deepfake speeches increasingly convincing, posing growing threats to security. While self-supervised learning (SSL) based detectors…
- arXiv cs.AIresearchWhen Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following
arXiv:2610.05278v1 Announce Type: cross Abstract: Verifiable instruction-following benchmarks often express each constraint through one fixed template. We test whether scores remain stable when the operational requiremen…
- arXiv cs.AIresearchRevisiting Ground-Truth Synthesis from High-Speed Video: Exact Validity Conditions and an Audited Consumer Capture Corpus
arXiv:2610.05298v1 Announce Type: cross Abstract: Motion-deblurring datasets are commonly synthesised by averaging $N$ consecutive high-frame-rate frames and labelling the result with the central frame. We show that this…
- arXiv cs.AIresearchCharacterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs
arXiv:2610.05305v1 Announce Type: cross Abstract: Large Language Model (LLM) inference has become the dominant workload in modern AI systems, requiring serving infrastructures to maximize throughput while meeting strict…
- arXiv cs.AIresearchGrammar-Guided Code Watermarking with Green Temperature
arXiv:2610.05323v1 Announce Type: cross Abstract: Large language model watermarking embeds detectable statistical signals during decoding, but the resulting changes to token probabilities can degrade generation quality.…
- arXiv cs.AIresearchCoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video
arXiv:2610.05324v1 Announce Type: cross Abstract: Partnered human-humanoid interaction couples locomotion with continuous physical contact. A humanoid needs to coordinate with a person's motion while responding to intera…
- arXiv cs.AIresearchVAMPS: Visual and Motor Policies from Sampling-Based Planning
arXiv:2610.05331v1 Announce Type: cross Abstract: Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Mot…
- arXiv cs.AIresearchGreen-Routed Neural Operators: Physics Determines Where the Network Reads
arXiv:2610.05337v2 Announce Type: replace-cross Abstract: We identify a mismatch between the physical role of transport fields in many PDEs and their usual role in neural operators: PDEs use them to select read coordinat…
- arXiv cs.AIresearchOn Semi-Markov Suboptimality in Hierarchical Reinforcement Learning
arXiv:2610.05338v1 Announce Type: cross Abstract: Hierarchical reinforcement learning uses temporally extended subtasks for exploration, yet committing to their execution can restrict both deployment and policy learning.…
- arXiv cs.AIresearchReflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
arXiv:2610.05346v1 Announce Type: cross Abstract: Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly…
- arXiv cs.AIresearchRethinking Tabular Foundation Models On Data Streams
arXiv:2610.05352v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this success, interest is g…
- arXiv cs.AIresearchOptimal Control with Learned Critics under Unmodeled State Dependencies
arXiv:2610.05359v1 Announce Type: cross Abstract: Model Predictive Control (MPC) provides a structured and constraint-aware mechanism for decision-making, but its reliance on optimization-friendly analytical dynamics mod…
- arXiv cs.AIresearchAutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models
arXiv:2610.05369v1 Announce Type: cross Abstract: The increasing complexity and scale of modern cyber-attacks demand intelligent and computationally efficient Intrusion Detection Systems (IDS). However, designing effecti…
- arXiv cs.AIresearchDistributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs
arXiv:2610.05378v1 Announce Type: cross Abstract: Collaborative learning typically exchanges model parameters: federated clients communicate updates, while independently adapted foundation models are combined by exchangi…
- arXiv cs.AIresearchDoes Explainability Survive Data Drift?
arXiv:2610.05379v1 Announce Type: cross Abstract: Model performance monitoring is a standard practice in machine learning deployments. Detection performance is tracked continuously, and model decay is expected as the rel…
- arXiv cs.AIresearchGNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation
arXiv:2610.05387v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on coding and reasoning benchmarks; however, their ability to solve graph-structured machine learning pr…
- arXiv cs.AIresearchNo Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models
arXiv:2610.05401v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods intervene at the…