AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchPolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence
arXiv:2609.37712v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over…
- arXiv cs.AIresearchMulti-Site Real-World Performance of Commercial AI for Pulmonary and Incidental Pulmonary Embolism Detection
arXiv:2609.37750v1 Announce Type: cross Abstract: Pulmonary embolism (PE) is a leading cause of cardiovascular mortality, yet the real-world performance of FDA-cleared AI detection models remains incompletely characteriz…
- arXiv cs.AIresearchHiRAE: Hierarchical Representation Autoencoding with Residual Budgets
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediat…
- arXiv cs.AIresearchA Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
arXiv:2609.37788v3 Announce Type: replace-cross Abstract: We propose a rubric for assessing expressed clinical reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART,…
- arXiv cs.AIresearchPredictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
arXiv:2609.37789v1 Announce Type: cross Abstract: Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this…
- arXiv cs.AIresearchGLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
arXiv:2609.37798v1 Announce Type: cross Abstract: Speech self-supervised learning aims to learn general-purpose representations for downstream speech tasks. However, current approaches rely on complex, carefully designed…
- arXiv cs.AIresearchChallenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation
arXiv:2609.37800v1 Announce Type: cross Abstract: Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two challenges: learning use…
- arXiv cs.AIresearchPixel-Level Transformers in Remote Sensing: A Canopy Height Case Study
arXiv:2609.37809v1 Announce Type: cross Abstract: Predicting canopy height from medium-resolution satellite imagery is a common and scalable approach for assessing the condition of the world's forests, which play a cruci…
- arXiv cs.AIresearchThinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and ma…
- arXiv cs.AIresearchPrivy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
arXiv:2609.37825v1 Announce Type: cross Abstract: Assigning credit to intermediate steps remains a central challenge in training Large Language Models (LLMs) on multi-step reasoning tasks with sparse terminal rewards, an…
- arXiv cs.AIresearchScaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
arXiv:2609.37842v1 Announce Type: cross Abstract: Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influence different behavio…
- arXiv cs.AIresearchIs manual software optimization a thing of the past?
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substan…
- arXiv cs.AIresearchHandAnthro: Automated Hand Anthropometry from a Single Image
arXiv:2609.37855v1 Announce Type: cross Abstract: Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manual landmarking. We pre…
- arXiv cs.AIresearchIt's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
arXiv:2609.37863v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model rather than incidental…
- arXiv cs.AIresearchLearning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
arXiv:2609.37868v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail…
- arXiv cs.AIresearchBoids of a Feather Flock Together - Evolving Prey Behaviours Under Different Predator Attack Strategies
arXiv:2609.37885v1 Announce Type: cross Abstract: Flocking and schooling are thought to have evolved partly as defences against predation, but how prey should balance social and escape tendencies may depend on the predat…
- arXiv cs.AIresearchBeyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction
arXiv:2609.37905v1 Announce Type: cross Abstract: Click-Through Rate prediction, a core task in recommendation and advertising systems, relies on modeling interactions among sparse categorical features. Explicit cross ne…
- arXiv cs.AIresearchGenerated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3
arXiv:2609.37911v1 Announce Type: cross Abstract: Scientific queries are often brief, while relevant papers use specialized vocabulary. Generated query expansion can bridge this mismatch, but earlier work suggests that i…
- arXiv cs.AIresearchThe Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
arXiv:2609.37914v1 Announce Type: cross Abstract: Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a phenomenon known as \emph{…
- arXiv cs.AIresearchRLX: A Unified Multi-Backend Tensor Compiler and Distributed Runtime in Rust
arXiv:2609.37916v1 Announce Type: cross Abstract: Production machine learning (ML) stacks often split graph compilation and kernel execution across different layers and languages, making backend behavior, deployment guar…
- arXiv cs.AIresearchRollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
arXiv:2609.37925v1 Announce Type: cross Abstract: Autoregressive (AR) video diffusion enables low-latency, streamable video generation, but prediction errors often accumulate over long rollouts. Training the generator on…
- arXiv cs.AIresearchDoes Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark
arXiv:2609.37938v1 Announce Type: cross Abstract: Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video acc…
- arXiv cs.AIresearchDagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
arXiv:2609.37972v1 Announce Type: cross Abstract: As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By q…
- arXiv cs.AIresearchOn Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The model is trained on ra…
- arXiv cs.AIresearch$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
arXiv:2609.37976v2 Announce Type: replace-cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacity lies in th…
- arXiv cs.AIresearchNo Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection
arXiv:2609.38004v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies s…
- arXiv cs.AIresearchFrom Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection
arXiv:2609.38010v1 Announce Type: cross Abstract: Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety monitoring, data colle…
- arXiv cs.AIresearchAuditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls
arXiv:2609.38021v2 Announce Type: replace-cross Abstract: This report audits evaluation of a long-term-memory retrieval chain on the 500 LongMemEval-S development questions. Its strongest historical reader lane scores 47…
- arXiv cs.AIresearchDr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD treats all teacher…
- arXiv cs.AIresearchGender bias across LLMs is common and highly heterogeneous
arXiv:2609.38036v2 Announce Type: replace-cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with real consequ…
- arXiv cs.AIresearchNeural topology optimization of ship structures under propulsion machinery vibrations
arXiv:2609.38089v1 Announce Type: cross Abstract: Ship structural vibrations contribute to noise, fatigue, and equipment damage, while dynamic-compliance topology optimization can produce pathological designs near resona…
- arXiv cs.AIresearchHow Local Mixing Encodes Relative Position in Global NoPE Attention
arXiv:2609.38109v1 Announce Type: cross Abstract: The attention operation is naively position invariant. However, positional information is fundamental to natural language, and therefore a variety of explicit position en…
- arXiv cs.AIresearchBreaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
arXiv:2609.38140v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes…
- arXiv cs.AIresearchBeyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
arXiv:2609.38155v1 Announce Type: cross Abstract: Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entiti…
- arXiv cs.AIresearchLeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA). Although…
- arXiv cs.AIresearchSTEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
arXiv:2609.38169v1 Announce Type: cross Abstract: Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serv…
- arXiv cs.AIresearchImplementing Cumulative Functions with Generalized Cumulative Constraints
arXiv:2508.01751v3 Announce Type: replace Abstract: Modeling scheduling problems with conditional time intervals and cumulative functions has become a common approach when using modern commercial constraint programming s…
- arXiv cs.AIresearchSequence Variables: A Constraint Programming Computational Domain for Routing and Sequencing
arXiv:2510.09373v2 Announce Type: replace Abstract: Constraint Programming (CP) offers an intuitive, declarative framework for modeling Vehicle Routing Problems (VRP). While classical successor-based CP models can be ada…
- arXiv cs.AIresearchNonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
arXiv:2602.05709v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) approximates the update of a pretrained weight matrix using the product of two low-rank matrices. However, standard LoRA follows an explicit-…
- arXiv cs.AIresearchBeyond Pixels: A Vector-to-Graph Framework for Reliable Schematic Auditing
arXiv:2602.11678v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even…
- arXiv cs.AIresearchFloCA: Towards Faithful and Logically Consistent Flowchart Reasoning
arXiv:2602.14035v2 Announce Type: replace Abstract: Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-specific flowchart to ac…
- arXiv cs.AIresearchCIRCLE: A Framework for Evaluating AI from a Real-World Lens
arXiv:2602.24055v5 Announce Type: replace Abstract: This study proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI system outcomes in deploym…
- arXiv cs.AIresearchOntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation
arXiv:2604.05468v3 Announce Type: replace Abstract: Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information within KG snapshots. A ke…
- arXiv cs.AIresearchTimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
arXiv:2605.01418v2 Announce Type: replace Abstract: Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing time-series generative…
- arXiv cs.AIresearchBoosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
arXiv:2605.27023v5 Announce Type: replace Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are…
- arXiv cs.AIresearchDiversifying RLVR Rollouts via First-Token Exploration
arXiv:2605.28295v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) trains reasoning models without labeled trajectories, using groups of verifier-scored rollouts to explore alternat…
- arXiv cs.AIresearchRater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v3 Announce Type: replace Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but the…
- arXiv cs.AIresearchJUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models
arXiv:2607.16207v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) test whether a candidate example was used to train a language model. Existing attacks on fine-tuned discrete diffusion language mode…
- arXiv cs.AIresearchBelief-Guided Decision Making with Uncertainty Gating in the Game of Go
arXiv:2607.26946v2 Announce Type: replace Abstract: Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural network policy. W…
- arXiv cs.AIresearchDecode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
arXiv:2608.12385v3 Announce Type: replace Abstract: As large language models serve ever more requests, cumulative inference cost is growing relative to the one-time cost of training. In typical serving, prompt prefill ru…