AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhere LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams
arXiv:2609.29333v1 Announce Type: cross Abstract: One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show its pitfalls we gra…
- arXiv cs.AIresearchArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
arXiv:2609.29349v2 Announce Type: replace-cross Abstract: ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate detection in Ara…
- arXiv cs.AIresearchDomain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models
arXiv:2609.29358v1 Announce Type: cross Abstract: Vision-language models such as CLIP achieve strong zero-shot classification, yet under distribution shift, visual embeddings drift from fixed text embeddings. Training-fr…
- arXiv cs.AIresearchFrom Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring
arXiv:2609.29370v1 Announce Type: cross Abstract: Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing…
- arXiv cs.AIresearchWST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection
arXiv:2609.29372v1 Announce Type: cross Abstract: The acoustic front-end determines which forensic cues a speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable multiscale coefficien…
- arXiv cs.AIresearchSegment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection
arXiv:2609.29384v2 Announce Type: replace-cross Abstract: Online handwriting provides a non-invasive and low-cost behavioral biomarker for Alzheimer's disease (AD) detection, as it reflects both cognitive planning and fi…
- arXiv cs.AIresearchRufus-Air: An Open LLM Post-Training Recipe
arXiv:2609.29421v2 Announce Type: replace-cross Abstract: Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Cod…
- arXiv cs.AIresearchDetecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study
arXiv:2609.29433v2 Announce Type: replace-cross Abstract: Background: Artificial intelligence (AI)-based glaucoma detection from colour fundus photographs (CFP) offers scalable screening, but performance may decline on e…
- arXiv cs.AIresearchFrame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed
arXiv:2609.29447v1 Announce Type: cross Abstract: Smart maritime infrastructures provide continuous access to heterogeneous sensing streams, enabling repeated experimentation, digital-twin development, and AI-based marit…
- arXiv cs.AIresearchAgriCountDINO: Parameter-Efficient Exemplar-Guided Counting and Localization in Agriculture
arXiv:2609.29460v1 Announce Type: cross Abstract: Accurate counting and localization of plants and their organs support phenotyping and yield estimation, yet target appearance, scale, and density vary widely across speci…
- arXiv cs.AIresearchDirect Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs
arXiv:2609.29466v1 Announce Type: cross Abstract: Approximate message passing on factor graphs underlies two dominant families of probabilistic inference algorithms: expectation propagation (EP) and variational message p…
- arXiv cs.AIresearchRoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots
arXiv:2609.29490v1 Announce Type: cross Abstract: Recent advances in robotics highlight hierarchical configurations of robot morphology, where multiple levels of functional substructures synergize to facilitate intellige…
- arXiv cs.AIresearchGenerative Evolutionary Design of Voxel-Based Soft Robots with Provable Optimality
arXiv:2609.29491v1 Announce Type: cross Abstract: Voxel-based soft robots (VSRs) present a promising avenue for developing artificial organisms with lifelike intelligence. However, the vast design spaces and expensive ev…
- arXiv cs.AIresearchWho Put the I in AI? Provenance and the Admissibility of Machine Self-Report
arXiv:2609.29494v1 Announce Type: cross Abstract: Large language models make statements concerning their own "minds". When asked whether or not they are conscious, they usually say that they are not; if they are prompted…
- arXiv cs.AIresearchPROOF: Profiling Reliability of Object-Level Facts in Large Language Models
arXiv:2609.29504v1 Announce Type: cross Abstract: Aggregate factuality scores hide where a language model succeeds, which relations it confuses, and whether an answer survives innocuous changes to the question or decoder…
- arXiv cs.AIresearchCoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites
arXiv:2609.29527v1 Announce Type: cross Abstract: Automated microscopy could widen access to malaria diagnosis in low-resource settings, but the deadliest species, P. falciparum, presents in its early ring stage as an ob…
- arXiv cs.AIresearchGeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning
arXiv:2609.29541v2 Announce Type: replace-cross Abstract: Referring segmentation in overhead imagery is inherently relational: a query may ask for the buildings north of the road or the pond closest to a residential area…
- arXiv cs.AIresearchGeneralized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse
arXiv:2609.29546v1 Announce Type: cross Abstract: The variational graph autoencoder (VGAE) regularizes its posterior toward the prior with the Kullback-Leibler divergence, a choice inherited from the variational autoenco…
- arXiv cs.AIresearchUNWIND: Any-Length Facial Video for Stress Detection without Temporal Windowing
arXiv:2609.29553v1 Announce Type: cross Abstract: Automatic stress recognition from facial video provides a non-contact approach for affective monitoring. However, most existing video-based methods divide complete record…
- arXiv cs.AIresearchCATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion
arXiv:2609.29591v1 Announce Type: cross Abstract: BraTS local synthesis replaces masked regions in T1-weighted brain MRI with plausible tumor-free tissue while preserving observed anatomy. We present CATCH, conditional 3…
- arXiv cs.AIresearchQINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models
arXiv:2609.29592v1 Announce Type: cross Abstract: Adapting large pretrained vision models under limited data and frozen-backbone constraints remains a central challenge in transfer learning. While lightweight adapters an…
- arXiv cs.AIresearchEvidence-Driven Differential Diagnosis of Malignant Melanoma
arXiv:2609.29613v1 Announce Type: cross Abstract: We present a modular and multi-level framework for the differential diagnosis of malignant melanoma. Our framework integrates contextual information and evidence at the l…
- arXiv cs.AIresearchAn Exploratory Ablation of a Small MLA--SSM Hybrid Language Model
arXiv:2609.29618v1 Announce Type: cross Abstract: We report an exploratory, single-seed ablation of TALH (Adaptive Latent Hybrid), a decoder-only language model with parallel Multi-head Latent Attention (MLA) and a custo…
- arXiv cs.AIresearchA Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes
arXiv:2609.29630v1 Announce Type: cross Abstract: Recent topic models leverage pretrained embeddings, but neural architectures produce latent representations without grounding in specific texts, and clustering-based pipe…
- arXiv cs.AIresearchTTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification
arXiv:2609.29633v1 Announce Type: cross Abstract: We present TTLab's submission to the AlexandriaX-2026 Subtask~3 on Arabic MT error span detection and classification. Our system frames the task as token-level classifica…
- arXiv cs.AIresearchOperator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
arXiv:2609.29636v2 Announce Type: replace-cross Abstract: Verified search, in which a language model proposes programs, a hard evaluator scores them, and selection keeps the best, has recently moved mathematical records;…
- arXiv cs.AIresearchInvestigating White Blood Cells as a Source of False-Positive Malaria Parasite Detection in African Blood-Smear Images
arXiv:2609.29663v1 Announce Type: cross Abstract: White blood cells (WBCs) present on every Giemsa-stained thick blood smear share visual properties with early-stage Plasmodium falciparum ring-form trophozoites: small si…
- arXiv cs.AIresearchDo World Models Make Better Robots? A Survey of Evaluation Benchmarks for Predictive Embodied Intelligence
arXiv:2609.29669v1 Announce Type: cross Abstract: Robot learning now advances along two tracks that rarely meet. On one side, direct Vision-Language-Action (VLA) policies map observations to actions and are scored by clo…
- arXiv cs.AIresearchThe Sequential Price of Continual Learning
arXiv:2609.29674v2 Announce Type: replace-cross Abstract: Sequential task updates are fundamental to continual learning, but their recency bias can impose a lasting performance cost. We study this cost in an overparamete…
- arXiv cs.AIresearchReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition
arXiv:2609.29678v1 Announce Type: cross Abstract: Semi-supervised fine-grained visual recognition is highly vulnerable to overconfident pseudo-label errors: visually similar categories frequently produce high-confidence…
- arXiv cs.AIresearchDecoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning
arXiv:2609.29711v1 Announce Type: cross Abstract: Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy gu…
- arXiv cs.AIresearchRevalidation Beats Stateful Routing for Scientific Surrogates Under Distribution Shift
arXiv:2609.29715v1 Announce Type: cross Abstract: Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input support, or physical…
- arXiv cs.AIresearchTopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening
arXiv:2609.29740v1 Announce Type: cross Abstract: Ligand-based virtual screening (LBVS) is a practical first-pass tool in early-stage drug discovery, but existing benchmarks can overestimate performance through random ne…
- arXiv cs.AIresearchBetween the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase
arXiv:2609.29744v1 Announce Type: cross Abstract: We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (…
- arXiv cs.AIresearchAnatomy-aware cross-speaker adaptation of complete vocal-tract acoustic-to-articulatory inversion
arXiv:2609.29766v1 Announce Type: cross Abstract: Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation framework that uses an…
- arXiv cs.AIresearchPrefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs
arXiv:2609.29775v1 Announce Type: cross Abstract: Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e., an output prefix, th…
- arXiv cs.AIresearchTimeBraid: Unifying Time Series and Language for Understanding and Forecasting
arXiv:2609.29792v1 Announce Type: cross Abstract: We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through inter…
- arXiv cs.AIresearchBenchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages
arXiv:2609.29798v1 Announce Type: cross Abstract: This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The…
- arXiv cs.AIresearchSEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search
arXiv:2609.29803v1 Announce Type: cross Abstract: Search quality evaluation provides essential supervision and diagnostic signals for the development and iteration of industrial search systems. Although large language mo…
- arXiv cs.AIresearchYour Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
arXiv:2609.29845v1 Announce Type: cross Abstract: While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct te…
- arXiv cs.AIresearchTemplate Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks
arXiv:2609.29851v1 Announce Type: cross Abstract: Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect di…
- arXiv cs.AIresearchMulti-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language
arXiv:2609.29855v1 Announce Type: cross Abstract: We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing…
- arXiv cs.AIresearchMorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots
arXiv:2609.29908v1 Announce Type: cross Abstract: Neural models can learn to generate various solutions to the inverse kinematics problem from data, but are usually limited to a single robot. We present MorphIK, a flow-m…
- arXiv cs.AIresearchStructured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation
arXiv:2609.29912v1 Announce Type: cross Abstract: With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sen…
- arXiv cs.AIresearchCultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations
arXiv:2609.29928v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, eva…
- arXiv cs.AIresearchAn Empirical Study of VLM Pipelines for Long-Document QA
arXiv:2609.29933v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deployi…
- arXiv cs.AIresearchWhen Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers
arXiv:2609.29937v1 Announce Type: cross Abstract: Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent…
- arXiv cs.AIresearchMind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
arXiv:2609.29940v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, of…
- arXiv cs.AIresearchTracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking
arXiv:2609.29951v1 Announce Type: cross Abstract: State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained to predict the runn…
- arXiv cs.AIresearchBeyond Average Safety: Chance-Constrained LLM Fine-tuning
arXiv:2609.29960v1 Announce Type: cross Abstract: Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on…