AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion
arXiv:2609.26039v2 Announce Type: replace-cross Abstract: Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative a…
- arXiv cs.AIresearchCricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching
arXiv:2609.26056v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) offer promising capabilities for automated sports coaching but face a fundamental limitation: they implicitly compare against professional s…
- arXiv cs.AIresearchObserving the Conduct of Systematic Reviews with Generative AI Support: An Experience Report from a Graduate Software Engineering Course
arXiv:2609.26057v1 Announce Type: cross Abstract: Context: Secondary studies are fundamental practices in Evidence- Based Software Engineering, but teaching them requires activities that expose students to authentic meth…
- arXiv cs.AIagentsPolicy-Backed Selective Regeneration under Tainted Inter-Agent Communication
arXiv:2609.26072v1 Announce Type: cross Abstract: Inter-agent communication is essential to multi-agent language-model systems, yet a single message may combine task-critical information with instructions not authorized…
- arXiv cs.AIresearchTSS: Target-Side Sparsification for Speculative Decoding in Domain-Specific Large Language Models
arXiv:2609.26100v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference through collaboration between a lightweight draft model and a target verifier. Existing methods mainly imp…
- arXiv cs.AIresearchCertified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods
arXiv:2609.26112v1 Announce Type: cross Abstract: Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded input neighbourhoods.…
- arXiv cs.AIresearchStepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots
arXiv:2609.26131v2 Announce Type: replace-cross Abstract: Large language models and vision-language models are increasingly used as high-level planners in robotic systems, using task goals and sensor summaries to select…
- arXiv cs.AIresearchTTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration
arXiv:2609.26151v1 Announce Type: cross Abstract: Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations. While recent architectures like Transformers…
- arXiv cs.AIresearchMGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning
arXiv:2609.26166v1 Announce Type: cross Abstract: Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temporal remote sensing…
- arXiv cs.AIresearchThe Uncontrolled Variable: Vision-Language Refusal Is Conditioned on the Image-Attachment Interface, and Not Robust to Irrelevant Image Properties
arXiv:2609.26174v2 Announce Type: replace-cross Abstract: We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding everything the request…
- arXiv cs.AIresearchRefusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation
arXiv:2609.26176v2 Announce Type: replace-cross Abstract: Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often the model complied.…
- arXiv cs.AIresearchMagnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression
arXiv:2609.26177v1 Announce Type: cross Abstract: Structured pruning of attention heads provides a hardware-friendly way to compress Transformer language models. However, existing methods for measuring head-level importa…
- arXiv cs.AIagentsSilent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems
arXiv:2609.26184v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning.…
- arXiv cs.AIresearchDynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs
arXiv:2609.26185v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit harmful or unintended c…
- arXiv cs.AIagentsWatchPoint: Executable User Feedback for Real-World Agentic Web Development
arXiv:2609.26204v1 Announce Type: cross Abstract: When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed…
- arXiv cs.AIresearchWhen Unpaired Sets Support Shared-Corruption Calibration: Moment Geometry and Two-Sample Precision
arXiv:2609.26209v1 Announce Type: cross Abstract: Collections of diverse observations often share one acquisition, processing, geometric, or channel corruption, while only an unpaired clean reference set is available. Fo…
- arXiv cs.AIresearchReducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation
arXiv:2609.26229v1 Announce Type: cross Abstract: Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification,…
- arXiv cs.AIresearchABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap
arXiv:2609.26237v1 Announce Type: cross Abstract: We present the ABAI submission to COLIEE 2026 Task 1, case law retrieval, together with a controlled study of why it underperformed. The task suppresses the cited passage…
- arXiv cs.AIresearchAIGC Video Detection based on the fusion of spatial-frequency-optical flow multimodal features
arXiv:2609.26274v1 Announce Type: cross Abstract: The rapid evolution of generative AI (e.g., Sora, Hunyuan) makes it essential to develop effective detection strategies that can generalize across ever-evolving synthesis…
- arXiv cs.AIresearchOn the security and privacy of LLMs in Mobility
arXiv:2609.26295v1 Announce Type: cross Abstract: The mobility sector is undergoing a paradigm shift driven by advances in Generative Artificial Intelligence. With a global market valued at approximately 2.9 trillion dol…
- arXiv cs.AIresearchCompKV: Compensation-Aware KV Selection for Long-Context LLM Inference
arXiv:2609.26300v1 Announce Type: cross Abstract: Despite their strong performance, large language models (LLMs) are bottlenecked by KV cache memory traffic during long-context inference. Sparse attention is widely used…
- arXiv cs.AIresearchTriWorldBench: A Tri-View Consistency Perspective on Embodied World Models
arXiv:2609.26314v1 Announce Type: cross Abstract: Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary…
- arXiv cs.AIresearchGeometry-Aware Hyperbolic Residual-Quantized Variational Autoencoders
arXiv:2609.26342v2 Announce Type: replace-cross Abstract: Residual Vector Quantization turns continuous representations into discrete, multi-level token sequences. Yet most methods operate in Euclidean space, despite the…
- arXiv cs.AIresearchTransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling
arXiv:2609.26347v2 Announce Type: replace-cross Abstract: The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP) tools. We pre…
- arXiv cs.AIresearchPACT: From Credit Assignment to Critic Alignment
arXiv:2609.26355v1 Announce Type: cross Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definiti…
- arXiv cs.AIresearchGitScholar: A Dataset for Predicting AI Research Impact from GitHub Engagement
arXiv:2609.26361v1 Announce Type: cross Abstract: With the rapid pace of AI research and the hundreds of daily new publications, staying up-to-date with the latest developments has become increasingly difficult. For rese…
- arXiv cs.AIresearchFairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks
arXiv:2609.26377v1 Announce Type: cross Abstract: Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing…
- arXiv cs.AIresearchMAVP: Map-Aware Visuomotor Policies for Mobile Manipulation
arXiv:2609.26378v1 Announce Type: cross Abstract: Successful mobile manipulation requires coordinated base and arm motion while maintaining accurate spatial positioning. However, demonstration-trained policies can strugg…
- arXiv cs.AIresearchTimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series
arXiv:2609.26389v1 Announce Type: cross Abstract: Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inher…
- arXiv cs.AIresearchQuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
arXiv:2609.26425v3 Announce Type: replace-cross Abstract: Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment b…
- arXiv cs.AIresearchDeepFEAv2: Deep Learning for Transient Finite Element Analysis Beyond Structured Meshes
arXiv:2609.26426v1 Announce Type: cross Abstract: Finite Element Analysis (FEA) is widely used for transient mechanical simulations, but its high computational cost limits real-time and high-resolution applications. Deep…
- arXiv cs.AIresearchComplementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings
arXiv:2609.26463v1 Announce Type: cross Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides s…
- arXiv cs.AIresearchPP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded Devices
arXiv:2609.26474v1 Announce Type: cross Abstract: Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedi…
- arXiv cs.AIresearchFeatLens: Feature-Guided Dependency Retrieval for Repository-Level Code Generation
arXiv:2609.26480v2 Announce Type: replace-cross Abstract: Retrieving task-relevant code dependencies is critical for repository-level code generation. Existing approaches obtain dependency context through similarity-base…
- arXiv cs.AIresearchNot Quite My Tempo: Voice Activity-aware Speech Synthesis for Lip-Synchronous Dubbing
arXiv:2609.26486v1 Announce Type: cross Abstract: Automatic lip-synchronous dubbing requires a speech synthesis model to generate alternating voice and silence patterns in the target language that match the timing of the…
- arXiv cs.AIresearchWhen Recursive Models Finish Computing
arXiv:2609.26487v1 Announce Type: cross Abstract: Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation…
- arXiv cs.AIresearchRadiomics-Conditioned Modulation of RenalCLIP Features for Clear Cell Renal Cell Carcinoma Classification
arXiv:2609.26492v1 Announce Type: cross Abstract: Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this co…
- arXiv cs.AIresearchThe Ethics of Artificial Intelligence in Military Operations
arXiv:2609.26507v1 Announce Type: cross Abstract: Deep learning systems now mediate military decisions to use force, yet their internal logic resists inspection, their evaluation practices are gameable, and their deploym…
- arXiv cs.AIresearchDo Vision Model See Like the Brain? A Comparison Across EEG Encoding Model
arXiv:2609.26512v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge at a specific point…
- arXiv cs.AIresearchA Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generation
arXiv:2609.26527v1 Announce Type: cross Abstract: When two texts describe the same expression, standard metrics based on lexical overlap or whole-text similarity may fail to detect meaningful differences in how that expr…
- arXiv cs.AIresearchTopology-Stratified Materials Discovery with A Flow-Based Generative Model
arXiv:2609.26547v1 Announce Type: cross Abstract: Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additi…
- arXiv cs.AIagentsThe Disciplinary Language Transfer Problem: How Psychological Vocabulary Produces Governance Failures in AI Agent Deployment
arXiv:2609.26562v1 Announce Type: cross Abstract: The vocabulary used to describe AI agents in governance contexts -- learning, memory, values, compliance, identity, trust -- is borrowed from psychological and organizati…
- arXiv cs.AIresearchReceptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
arXiv:2609.26579v1 Announce Type: cross Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on soc…
- arXiv cs.AIresearchHierarchical GNNs for power flow: letting physics shape the hierarchy
arXiv:2609.26603v3 Announce Type: replace-cross Abstract: Hierarchical latent communication improves the generalization of a power-flow model, shared across three grids, to new operating scenarios. The module exchanges i…
- arXiv cs.AIresearchGreedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference
arXiv:2609.26621v1 Announce Type: cross Abstract: Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm pro…
- arXiv cs.AIresearchCapable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
arXiv:2609.26637v1 Announce Type: cross Abstract: The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-sour…
- arXiv cs.AIresearchA Spectral Theory of Grokking: Weight Decay induces Feature Learning
arXiv:2609.26679v1 Announce Type: cross Abstract: In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent…
- arXiv cs.AIagentsFrom Alignment to Access Control: A Framework for GenAI Policy Enforcement
arXiv:2609.26682v1 Announce Type: cross Abstract: Generative AI (GenAI) applications have flourished enabling users to chat with large language models, and to create agents to act on their behalf for a variety of tasks.…
- arXiv cs.AIagentsMeasuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
arXiv:2609.26693v1 Announce Type: cross Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local…
- arXiv cs.AIresearchBeyond Repeated Sampling: Learning Search Policies for LLM Reasoning
arXiv:2609.26704v1 Announce Type: cross Abstract: Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many…