AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMulti-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications
arXiv:2609.33282v1 Announce Type: new Abstract: Subjective judgments are central to many high-traffic applications, but subjective intensity is difficult to quantify and perceptions vary substantially across individuals.…
- arXiv cs.AIresearchRINI: Seeing the Prior Is Not Enough
arXiv:2609.33284v1 Announce Type: new Abstract: A research proposal can describe an established mechanism correctly while claiming to introduce it. We study whether providing the earlier paper corrects such contribution…
- arXiv cs.AIresearchFeedback Makes Perfect: A Closed-Loop Framework for NL-to-STL Translation
arXiv:2609.33287v1 Announce Type: new Abstract: Signal Temporal Logic (STL) enables rigorous verification and control of cyber-physical systems, but writing correct specifications requires expertise that most requirement…
- arXiv cs.AIresearchThe Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization
arXiv:2609.33297v1 Announce Type: new Abstract: Verifying multi-step LLM reasoning requires more than determining whether a trace is correct: a useful verifier should identify where the reasoning first goes wrong. Howeve…
- arXiv cs.AIresearchPhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning
arXiv:2609.33319v1 Announce Type: new Abstract: A key challenge in physics diagram understanding is correctly associating visual information with the physical entities, relations, and conditions it describes. Even when a…
- arXiv cs.AIresearchNaturalness-guided Manifold Flow Matching for Sign Language Production
arXiv:2609.33339v1 Announce Type: new Abstract: Sign Language Production (SLP) aims to generate sign motions from text. Conditional Flow Matching methods have achieved strong performance in SLP by constructing conditiona…
- arXiv cs.AIresearchQuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG
arXiv:2609.33351v1 Announce Type: new Abstract: Fidelity-based quantum retrieval ranks candidates by the fidelity between query and archive states. Applying a shared input-independent unitary after fixed state encoding l…
- arXiv cs.AIresearchUnmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models
arXiv:2609.33355v1 Announce Type: new Abstract: Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference decision. Existing methods vary in how they prioritize…
- arXiv cs.AIresearchDrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling
arXiv:2609.33368v1 Announce Type: new Abstract: Real-world time series contain evolving underlying dynamics with irregular variations that lack stable temporal patterns and are often referred to as noise. Existing method…
- arXiv cs.AIresearchCross-modal Translation via Conditional Latent Denoising for Video Deepfake Detection
arXiv:2609.33394v1 Announce Type: new Abstract: The growing threat of video deepfakes necessitates multimodal detection. Beyond serving as independent indicators of authenticity, audio and visual signals have intrinsic d…
- arXiv cs.AIresearchCoViST: Visual Token Compression via Composable States
arXiv:2609.33397v1 Announce Type: new Abstract: Visual token compression lowers the inference cost of vision--language models by representing images with fewer tokens. However, most existing methods compress visual token…
- arXiv cs.AIresearchCOEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement
arXiv:2609.33398v1 Announce Type: new Abstract: Recursive self-improvement (RSI) seeks to move large language models beyond static training pipelines toward systems that can participate in improving their own future beha…
- arXiv cs.AIresearchMetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
arXiv:2609.33411v1 Announce Type: new Abstract: Rapid progress in Large Language Models (LLMs) is saturating static benchmarks faster than they can be designed. While existing automated evolution frameworks attempt to ge…
- arXiv cs.AIresearchTemporal Graph Learning of Wearable Actigraphy and Sleep Traces for Modelling Adolescent Crystallized Intelligence
arXiv:2609.33428v1 Announce Type: new Abstract: Wearable actigraphy offers a scalable, ecologically valid alternative to episodic clinical assessment. However, predicting continuous adolescent crystallized intelligence (…
- arXiv cs.AIresearchMAC-Net: A Multi-Task Deep Learning Framework for Modeling Cognitive Function From Task-Based fMRI
arXiv:2609.33440v1 Announce Type: new Abstract: Objective cognitive assessment from neural signals supports neurorehabilitation, but individual-level prediction from task-based fMRI (tfMRI) remains difficult because neur…
- arXiv cs.AIresearchWhat Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation
arXiv:2609.33455v2 Announce Type: replace Abstract: On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since each update is conditi…
- arXiv cs.AIresearchWhen Does the Concept of "Dog" Emerge in an Audio LLM?
arXiv:2609.33458v1 Announce Type: new Abstract: Multimodal large language models answer audio questions, but how they represent auditory semantics and use them in decisions remains unclear, limiting our understanding of…
- arXiv cs.AIresearchJust Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs
arXiv:2609.33477v1 Announce Type: new Abstract: Hybrid LLMs interleave full-attention layers with linear-attention layers to reduce long-context inference cost, but this structure complicates prefix caching. Full-attenti…
- arXiv cs.AIresearchRelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse
arXiv:2609.33503v1 Announce Type: new Abstract: Cross-request KV caching reduces the prefill cost of Retrieval-Augmented Generation (RAG), but conventional prefix caching severely limits cache reuse across requests. Posi…
- arXiv cs.AIresearchWhen Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing
arXiv:2609.33505v1 Announce Type: new Abstract: Modern learned systems increasingly combine learned components with search, repair, or external solvers. Benchmarks often measure the resulting end-to-end system, while sci…
- arXiv cs.AIresearchPPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment
arXiv:2609.33516v1 Announce Type: new Abstract: Photoplethysmography (PPG) is widely recorded by clinical monitors and consumer wearables, providing a scalable source of continuous physiological information. These record…
- arXiv cs.AIresearchReasoning on the Simplex: Geometric Fixed-Point Models
arXiv:2609.33540v1 Announce Type: new Abstract: Looped reasoners spend test-time compute by iterating a weight-tied map, but a small residual does not mean the state is a fixed point when that map lives in unconstrained…
- arXiv cs.AIresearchOSCC: Certified Observation-Safe Coupling Optimization for Gradient-Noise Control in Imperfect-Information Learning
arXiv:2609.33543v2 Announce Type: replace Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from serving as a general…
- arXiv cs.AIresearchOpenFC: Learning Verification Policies towards Open-Search Fact Checking
arXiv:2609.33579v1 Announce Type: new Abstract: Open-search fact checking is not merely retrieval followed by classification, but a sequential decision problem in which every query, source visit, and stopping decision re…
- arXiv cs.AIresearchJustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization
arXiv:2609.33601v1 Announce Type: new Abstract: Recent generative models have become increasingly powerful, but their inference cost continues to grow. Model quantization offers a promising way to compress these models a…
- arXiv cs.AIresearchSupervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing
arXiv:2609.33610v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Exist…
- arXiv cs.AIresearchEAT: Expert Account Tracker for Efficient MoE Inference
arXiv:2609.33614v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have emerged as a revolutionary method to scale Transformer models. However, traditional MoE architecture still suffers from inefficiency si…
- arXiv cs.AIresearchScalable and Data-Driven Decision Support in the Maintenance, Repair, and Overhaul Process
arXiv:2609.33641v1 Announce Type: new Abstract: Several businesses apply maintenance, repair, and overhaul (MRO) principles to the life-cycle of their existing products. In cases like casted gas turbine component Product…
- arXiv cs.AIresearchAudit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
arXiv:2609.33662v2 Announce Type: replace Abstract: Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates disc…
- arXiv cs.AIresearchRSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games
arXiv:2609.33669v2 Announce Type: replace Abstract: Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide heterogeneous degr…
- arXiv cs.AIresearchTopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization
arXiv:2609.33688v1 Announce Type: new Abstract: Deep learning has emerged as an efficient alternative for predicting high-performance material distributions in topology optimization. Existing methods struggle to accurate…
- arXiv cs.AIresearchOne Latent, Many Tokens: Jointly Learning Compressed Embeddings for Efficient Language Diffusion
arXiv:2609.33698v1 Announce Type: new Abstract: Most continuous diffusion language models process one latent position per token at each sampling step, making generation expensive. Two-stage methods lower the cost by redu…
- arXiv cs.AIresearchSpecRead: A Benchmark for Measuring Whether Language Models Understand Hardware Specifications
arXiv:2609.33699v1 Announce Type: new Abstract: Existing benchmarks for large language models (LLMs) in hardware design evaluate downstream artifacts such as generated RTL, assertions, or testbenches. When a model fails…
- arXiv cs.AIresearchDoes Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse
arXiv:2609.33707v1 Announce Type: new Abstract: Vision-language-action (VLA) models adapt pretrained vision-language models (VLMs) for closed-loop robot control, transferring their perceptual and semantic capabilities to…
- arXiv cs.AIresearchBIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation
arXiv:2609.33713v1 Announce Type: new Abstract: Adapting general-purpose multimodal large language models (MLLMs) to specialized domains requires learning domain-specific decision criteria, which often hinge on subtle vi…
- arXiv cs.AIresearchRobust Biomolecular Complex Design Across Protein Conformational Landscapes
arXiv:2609.33726v2 Announce Type: replace Abstract: Proteins populate conformational ensembles, yet structure-based biomolecular design typically optimizes candidates against a single target conformation. Consequently, a…
- arXiv cs.AIresearchIs your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative
arXiv:2609.33786v1 Announce Type: new Abstract: A diffusion model can predict a follow-up medical scan from a baseline, but a clinician needs a per-voxel map of where that prediction can be trusted. Many such maps approx…
- arXiv cs.AIresearchDual-Vocabulary Language Model for Cross-Tokenizer Distillation
arXiv:2609.33816v1 Announce Type: new Abstract: On-policy distillation (OPD) bridges teacher supervision and student behavior, but different teacher-student tokenizers introduce misalignment in both input tokenization (#…
- arXiv cs.AIresearchHow code helps different tasks? A decompositional lens on LLM post-training
arXiv:2609.33845v1 Announce Type: new Abstract: Evaluating code data as a single corpus can obscure which types of code data benefit which models and downstream tasks. Effective data selection requires understanding both…
- arXiv cs.AIresearchCurating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges
arXiv:2609.33878v2 Announce Type: replace Abstract: Merchant matching resolves a noisy payment descriptor to a retrieved merchant entity or returns no match. A key challenge in curating training labels is distinguishing…
- arXiv cs.AIresearchEHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events
arXiv:2609.34007v2 Announce Type: replace Abstract: Electronic health records (EHRs) encode clinical histories as (time, modality, code) tuples, whereas pretrained language models expect text tokens. Serializing tuples a…
- arXiv cs.AIresearchA Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8
arXiv:2609.34015v2 Announce Type: replace Abstract: Phishing remains one of the most common vectors for financial and identity fraud, and most detection systems still rely on inspecting a page's URL, HTML markup, or doma…
- arXiv cs.AIresearchJev in Medicine: A Benchmark Evaluation
arXiv:2609.34024v4 Announce Type: replace Abstract: Jev is a non-generative System One model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and calibration on medical…
- arXiv cs.AIresearchThinking Outside the Box: Retention and Transmission of Information in Sliding-Window KV Inference
arXiv:2609.34049v1 Announce Type: new Abstract: Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretr…
- arXiv cs.AIresearchGenoMorph: Pathway-Grounded Genomic Disease Reasoning via Adaptive Latent Computation
arXiv:2609.34079v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in biological reasoning; however, genomic disease inference remains largely dependent on memorized gene-d…
- arXiv cs.AIresearchK-OPSD: Verifiable On-Policy Self-Distillation for Post-Training Vision-Language Models on AEC Drawings
arXiv:2609.34082v1 Announce Type: new Abstract: Interpreting architecture, engineering, and construction (AEC) drawings is hard for general Multimodal Large Language Models (MLLMs) and vision-language models (VLMs). We i…
- arXiv cs.AIresearchA Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Stream
arXiv:2609.34103v1 Announce Type: new Abstract: Refining a sequence of coarse 3D bounding boxes against a LiDAR point-cloud stream demands tracks that are geometrically accurate (high IoU) and temporally coherent (low ro…
- arXiv cs.AIresearchSpecRegMatch: Robust Semi-Supervised Regression for Vehicle Interior Noise Prediction
arXiv:2609.34111v1 Announce Type: new Abstract: The rapid advancement of artificial intelligence has observed increased application in predicting vehicle interior noise levels within the automotive industry. However, the…
- arXiv cs.AIresearchYou Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
arXiv:2609.34137v1 Announce Type: new Abstract: Concept unlearning in text-to-image diffusion models aims to suppress a target concept (e.g., \texttt{horse}) while preserving related but distinct content (e.g., \texttt{d…
- arXiv cs.AIresearchRAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints
arXiv:2609.34179v1 Announce Type: new Abstract: Retrieval-augmented generation systems are extensively instrumented with metrics, benchmarks, traces, and automated judges, but these tools do not decide whether a proposed…