AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos
arXiv:2609.17843v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is an actively studied task, having wide applications in typical scenarios such as public surveillance and road traffic safety. The task is…
- arXiv cs.AIresearchAfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content
arXiv:2609.17853v1 Announce Type: cross Abstract: AfriSyCo studies answer switching around African-language factual content with two complementary layers: native-language follow-ups and a controlled cross-language factor…
- arXiv cs.AIresearchWho Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels
arXiv:2609.17857v1 Announce Type: cross Abstract: Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four open-weight families…
- arXiv cs.AIresearchDoes AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming
arXiv:2609.17883v1 Announce Type: cross Abstract: The rapid adoption of generative AI has made final artifacts unreliable evidence of student learning, and AI detectors that examine only the finished product are inaccura…
- arXiv cs.AIresearchWalking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds
arXiv:2609.17901v1 Announce Type: cross Abstract: Generative modeling of time-dependent data is typically formulated on a discrete temporal grid, restricting supervision to the observed timestamps in the training data. W…
- arXiv cs.AIresearchEDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing
arXiv:2609.17953v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) can produce Natural Language Explanations (NLEs) that sound plausible yet remain inconsistent with the visual evidence they cite. We present…
- arXiv cs.AIresearchThe Attention Within: Consensus Dynamics in Selective State Space Models
arXiv:2609.17997v1 Announce Type: cross Abstract: Selective state space models (SSMs) have recently emerged as a compelling alternative to transformers, combining competitive performance with substantially improved infer…
- arXiv cs.AIresearchNewer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations
arXiv:2609.18007v1 Announce Type: cross Abstract: Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether newer models are fa…
- arXiv cs.AIresearchPhysics-Informed Neural Networks for Fast Multilayer Spectral Inversion of H{\alpha} 6562.8 A and Ca II 8542.1 A Spectra
arXiv:2609.18025v1 Announce Type: cross Abstract: Strong chromospheric absorption lines such as H$\alpha$ 6562.8 A and Ca II 8542.1 A provide vital diagnostics of plasma dynamics and thermal structure in the solar chromo…
- arXiv cs.AIresearchAn Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks
arXiv:2609.18052v1 Announce Type: cross Abstract: This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (…
- arXiv cs.AIresearchFrom a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale
arXiv:2609.18068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains such as housing screening. While alignment techniques mitigate explicit racial bias in gener…
- arXiv cs.AIresearchMask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration
arXiv:2609.18088v1 Announce Type: cross Abstract: Detection-free methods for image-to-point cloud registration are prone to erroneous correspondences caused by domain and modality discrepancies, limited sensitivity of fe…
- arXiv cs.AIresearchLinguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment
arXiv:2609.18106v1 Announce Type: cross Abstract: Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these create under the EU A…
- arXiv cs.AIresearchRethinking How We Evaluate Methodological Progress in Health AI
arXiv:2609.18134v2 Announce Type: replace-cross Abstract: Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work better, and…
- arXiv cs.AIresearchMoRE: Mixture of Reused Experts
arXiv:2609.18176v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the numb…
- arXiv cs.AIresearchBeyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers
arXiv:2609.18204v1 Announce Type: cross Abstract: Organizations increasingly use oversight loops where one large language model (LLM) audits another's outputs alongside procedural traces of claimed steps. A common concer…
- arXiv cs.AIresearchCapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026
arXiv:2609.18206v1 Announce Type: cross Abstract: The MUMU track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge requires a single unified multimodal model to jointly solve image tagging (Task A), open…
- arXiv cs.AIresearchA Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification
arXiv:2609.18212v1 Announce Type: cross Abstract: Over the years, Convolutional Neural Networks (CNNs) have demonstrated strong capability in cancer detection and classification using medical images. However, CNN-based m…
- arXiv cs.AIresearchCPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling
arXiv:2609.18216v2 Announce Type: replace-cross Abstract: Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches…
- arXiv cs.AIresearchAPGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study
arXiv:2609.18219v1 Announce Type: cross Abstract: Quantum Reinforcement Learning (QRL) represents policies as variational quantum circuits (VQCs), making it attractive for combinatorial optimization such as the Capacitat…
- arXiv cs.AIresearchRemembering Solomon Marcus
arXiv:2609.18224v1 Announce Type: cross Abstract: From the manifest of Andre Breton, through the transdisciplinary understanding, we arrive at a post-modern manifest. A talk by Laura De Marco (Harvard) will provide scien…
- arXiv cs.AIresearchQuanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
arXiv:2609.18248v1 Announce Type: cross Abstract: An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-neighbour index, a fu…
- arXiv cs.AIresearchM2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models
arXiv:2609.18259v2 Announce Type: replace-cross Abstract: Recent advancements have successfully adapted autoregressive language models to process multimodal signals, such as images and actions. Since raw action signals a…
- arXiv cs.AIresearchI code or AI code: A comparative evaluation of AI-rated scores in classroom observations
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet they remain resource-…
- arXiv cs.AIresearchKnowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering
arXiv:2609.18317v2 Announce Type: replace-cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such as Latin Amer…
- arXiv cs.AIresearchTrajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers
arXiv:2609.18321v2 Announce Type: replace-cross Abstract: Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same…
- arXiv cs.AIresearchLook Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR
arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has bec…
- arXiv cs.AIresearchSemantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction
arXiv:2609.18368v2 Announce Type: replace-cross Abstract: Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the down…
- arXiv cs.AIresearchGYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models
arXiv:2609.18384v1 Announce Type: cross Abstract: We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains and roles (hence GYR…
- arXiv cs.AIresearchReliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
arXiv:2609.18396v1 Announce Type: cross Abstract: Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical syste…
- arXiv cs.AIresearchA Non-Linear Neuron Based Detection of Isolated Pixels in Binary and Grayscale Images using Contrast Sensitive Receptive Fields
arXiv:2609.18399v1 Announce Type: cross Abstract: Identifying isolated points is important in image processing applications such as medical imaging, astronomy and quality control management. Other domains, such as cybers…
- arXiv cs.AIresearchTERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
arXiv:2609.18407v2 Announce Type: replace-cross Abstract: Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, wa…
- arXiv cs.AIresearchMultitask Reinforcement Learning for Assisting Choice Model Specification
arXiv:2609.18441v1 Announce Type: cross Abstract: Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and…
- arXiv cs.AIresearchCSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
arXiv:2609.18462v5 Announce Type: replace-cross Abstract: FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts. Their reconstruction-oriented re…
- arXiv cs.AIresearchActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
arXiv:2609.18487v1 Announce Type: cross Abstract: Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands…
- arXiv cs.AIresearchMiST: Mid-Training LLMs for Cybersecurity
arXiv:2609.18496v1 Announce Type: cross Abstract: Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security…
- arXiv cs.AIresearchVoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing benchmarks and models hav…
- arXiv cs.AIresearchInterpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations
arXiv:2609.18555v1 Announce Type: cross Abstract: Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble membe…
- arXiv cs.AIresearchOn-the-Fly Homographies Calibration for Multi-Camera Tracking
arXiv:2609.18582v1 Announce Type: cross Abstract: Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments. Pri…
- arXiv cs.AIresearchLabel-free steering: Compressing test-time reinforcement learning into bias-only subspaces
arXiv:2609.18587v3 Announce Type: replace-cross Abstract: Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically opti…
- arXiv cs.AIresearchOnline Robust Reinforcement Learning Through Monte-Carlo Planning
arXiv:2609.18599v1 Announce Type: cross Abstract: Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real…
- arXiv cs.AIresearchGenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media
arXiv:2609.18634v1 Announce Type: cross Abstract: Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or int…
- arXiv cs.AIresearchBeyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification
arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce priva…
- arXiv cs.AIresearchGeneralist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging
arXiv:2609.18688v1 Announce Type: cross Abstract: AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (…
- arXiv cs.AIresearchEcho: Learning-based Matching Decompilation using Trusted Back Translation
arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompilation addresses this…
- arXiv cs.AIresearchRethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
arXiv:2609.18708v1 Announce Type: cross Abstract: In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy…
- arXiv cs.AIresearchA Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages
arXiv:2609.18739v1 Announce Type: cross Abstract: Poor quality or noisy annotations in Named Entity Recognition (NER), as in any other NLP task, make it challenging to achieve state-of-the-art performance. In this paper,…
- arXiv cs.AIresearchUsing OCR Heads to Verbalize Image Semantics
arXiv:2609.18823v1 Announce Type: cross Abstract: How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Ac…
- arXiv cs.AIresearchGrainSpeech: Less Context, More Detail for Compact Speech Synthesis
arXiv:2609.18856v1 Announce Type: cross Abstract: Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram supervision. A recep…
- arXiv cs.AIresearchDecodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
arXiv:2609.18860v2 Announce Type: replace-cross Abstract: When large vision-language models misclassify harmful memes, the failure may reflect missing internal evidence or an inability to route represented evidence to th…