AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhen Does Domain Adaptation Help on Physical Vibration Sensors? A Held-Out-Bearing Study of Neural-Operator and Convolutional Models
arXiv:2609.31639v1 Announce Type: cross Abstract: Diagnosing rolling-element bearing faults from vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation under operating-condition…
- arXiv cs.AIresearchMeasure Learning at Steady State: A BIRD-SQL Formula 1 Case Study
arXiv:2609.31640v1 Announce Type: cross Abstract: Continual Learning Bench scores learning as short-horizon gain versus a reset baseline and finds naive full-context ICL strongest among the memories it tested. We treat I…
- arXiv cs.AIresearchInformation Design Against Gaming and Learning Adversaries
arXiv:2609.31643v1 Announce Type: cross Abstract: A principal who deploys a binary classifier with an abstention option must decide which queries the mechanism abstains on. The right choice depends on the adversary. A ga…
- arXiv cs.AIresearchMaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement Learning
arXiv:2609.31644v1 Announce Type: cross Abstract: Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from binary verifiers…
- arXiv cs.AIresearchSTAR: Adaptive Spatial-Temporal Normalization for Unified Microservice Incident Management
arXiv:2609.31645v2 Announce Type: replace-cross Abstract: Automated incident management in large-scale microservice systems relies on learning robust representations from multimodal observability data, including metrics,…
- arXiv cs.AIresearchMeasurement-Error-Aware Causal Distributed-Lag Quantile Modeling of Indoor Air Pollution and Short-Term Lung-Function Deterioration
arXiv:2609.31646v1 Announce Type: cross Abstract: Low-cost indoor air-quality sensors could support personalized asthma prevention, but their nonlinear measurement error, delayed exposure effects, time-varying confoundin…
- arXiv cs.AIresearchEnergy Vision--Language--Action: A Controlled Multimodal Benchmark for Intent-Conditioned Residential Energy Management
arXiv:2609.31648v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are studied mainly in robotics, where visual observations and language instructions are mapped to physical actions. This paper introdu…
- arXiv cs.AIresearchFrom Hand-Crafted to LLM-Based Variation Operators in Metaheuristics: A Tutorial
arXiv:2609.31649v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being employed as variation operators in metaheuristics, generating or modifying candidate solutions, heuristics, or program…
- arXiv cs.AIresearchPalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions
arXiv:2609.31651v1 Announce Type: cross Abstract: Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) handle culturally dive…
- arXiv cs.AIresearchOpen-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering
arXiv:2609.31652v1 Announce Type: cross Abstract: We present Open-Qwen-Music, an open reconstruction of Qwen-Music and a fully specified research system for text-to-music generation that couples LLM-based semantic compos…
- arXiv cs.AIresearchTemporal-Attention Head Specialization During Video Diffusion Training
arXiv:2609.31654v2 Announce Type: replace-cross Abstract: Video diffusion transformers depend on temporal attention to coordinate information across frames, yet nearly everything known about this mechanism comes from ana…
- arXiv cs.AIresearchFrom Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness
arXiv:2609.31656v1 Announce Type: cross Abstract: Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources of degradation, lab…
- arXiv cs.AIresearchEnhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling
arXiv:2609.31657v1 Announce Type: cross Abstract: Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not well characterized.…
- arXiv cs.AIresearchCross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification
arXiv:2609.31658v1 Announce Type: cross Abstract: Ship classification from Synthetic Aperture Radar (SAR) imagery is a critical computer vision task, yet the robustness of models under deployment shifts remains unclear.…
- arXiv cs.AIresearchParser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents
arXiv:2609.31660v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) pipelines are typically assembled from independently-chosen components -- a document parser, a chunking strategy, and an embedding mo…
- arXiv cs.AIresearchWhat Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks
arXiv:2609.31664v1 Announce Type: cross Abstract: Recent work suggests that obscure language registers can weaken large language model refusal behavior, especially when paired with black-box prompt optimization. It remai…
- arXiv cs.AIresearchAge-Adaptive Handwriting Reconstruction from an IMU-Based Digital Pen through Shared Representations and Domain-Specific Heads
arXiv:2609.31666v1 Announce Type: cross Abstract: Digital pens are widely used to capture handwriting on digital devices, enabling precise trace recording and enhancing human-computer interaction. However, most are bundl…
- arXiv cs.AIresearchQuery-aligned video frame selection for long video understanding
arXiv:2609.31668v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) process multimodal inputs by converting text, images, and videos into token sequences that are subsequently processed by a backbo…
- arXiv cs.AIresearchUnsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data
arXiv:2609.31671v1 Announce Type: cross Abstract: Event cameras are well suited to pedestrian crossing detection, and spiking neural networks (SNNs) can process their output natively, but current SNN detectors are traine…
- arXiv cs.AIresearchToward AI-Assisted Poultry Coccidiosis Diagnosis: Evaluating Gemini and BiomedParse on Eimeria Microscopy Images
arXiv:2609.31679v1 Announce Type: cross Abstract: Coccidiosis caused by Eimeria parasites is a major economic burden in poultry production, and effective control depends on accurate species-level diagnosis. This study ev…
- arXiv cs.AIresearchDoes Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?
arXiv:2609.31680v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting t…
- arXiv cs.AIresearchWhat does FFN compression change downstream? Same-state causal restoration in diffusion language models
arXiv:2609.31685v1 Announce Type: cross Abstract: Diffusion language models (DLMs) enable flexible, parallel generation, but their iterative denoising remains computationally expensive, motivating increasingly aggressive…
- arXiv cs.AIresearchAdapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection
arXiv:2609.31690v1 Announce Type: cross Abstract: Explainable Artificial Intelligence (XAI) solutions are essential for building trust in AI technologies and their integration in real manufacturing lines. However, most e…
- arXiv cs.AIresearchIntegrated Deep Learning Framework Designed on Hybrid Optimization Strategies for Automated Health Detection and Analysis in Silkworms
arXiv:2609.31701v1 Announce Type: cross Abstract: A Hybrid Residual Attention Network is proposed for accurately classifying silkworm images into six different classes, including healthy and diseased states. It uses resi…
- arXiv cs.AIresearchCan't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level
arXiv:2609.31706v1 Announce Type: cross Abstract: Visual Language Models (VLMs) have achieved remarkable success across diverse tasks, yet they struggle with high-resolution inputs where critical information resides in s…
- arXiv cs.AIresearchFrequency-Domain AI-Generated Image Detection: Exploring Decoder and Channel Attention for Feature Refinement
arXiv:2609.31723v1 Announce Type: cross Abstract: With the rapid progress of AI, the number of AI-generated images has increased significantly in recent years. However, the increasing variety of image generation models m…
- arXiv cs.AIresearchSWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation
arXiv:2609.31725v1 Announce Type: cross Abstract: Video Object Segmentation (VOS) aims to accurately segment target objects from consecutive video frames and track the changes of the objects in each frame of the video. C…
- arXiv cs.AIresearchHigh-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacement
arXiv:2609.31726v1 Announce Type: cross Abstract: Collaborative medical AI platforms allow researchers to train models on sensitive imaging data while restricting data export. However, trained models can serve as covert…
- arXiv cs.AIresearchGERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation
arXiv:2609.31731v1 Announce Type: cross Abstract: In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentatio…
- arXiv cs.AIresearchLukeNet: A lightweight CNN integrated with an XAI model for Smart acute lymphoblastic leukemia detection and management
arXiv:2609.31736v1 Announce Type: cross Abstract: Acute Lymphoblastic Leukemia (ALL) patients require early, accurate detection to enable timely treatment and effective patient management. A Convolutional Neural Network…
- arXiv cs.AIresearchPRIME-ANC: Path-Ratio-Informed Modeling for Efficient Neural Filter Synthesis in Active Noise Control
arXiv:2609.31772v1 Announce Type: cross Abstract: Changes in listener acoustics require active noise control (ANC) filters to be redesigned for new acoustic paths. We introduce PRIME-ANC, a shared neural synthesizer that…
- arXiv cs.AIresearchOptimal transport meets speech: a tutorial review
arXiv:2609.31787v1 Announce Type: cross Abstract: Optimal Transport (OT) provides a principled framework for comparing and transforming probability distributions while preserving geometric structure. Recently, OT has gai…
- arXiv cs.AIresearchSame Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?
arXiv:2609.31796v1 Announce Type: cross Abstract: Activation probes are increasingly used to monitor LLMs in deployment. A probe is typically trained under one inference configuration, then used under whatever batch size…
- arXiv cs.AIresearchVideo-to-Music Generation for Gameplay Videos
arXiv:2609.31810v2 Announce Type: replace-cross Abstract: Video-to-music models have advanced considerably in the last few years, particularly in film and music video applications. In this paper, we investigate this prob…
- arXiv cs.AIresearchA Surgical Foundation Model Reveals Task-Dependent Label Efficiency
arXiv:2609.31821v1 Announce Type: cross Abstract: Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised foundation models ad…
- arXiv cs.AIresearchSynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
arXiv:2609.31823v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have demonstrated remarkable performance on multimodal reasoning benchmarks, yet their perceptual reliability under physically constr…
- arXiv cs.AIresearchPHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning
arXiv:2609.31855v1 Announce Type: cross Abstract: Human demonstrations provide dense policy-level information but sometimes lack local precision. Human feedback presents accurate local critiques, but offers sparse evalua…
- arXiv cs.AIresearchAirLog: Store-Level Indoor Life Logging Made Easy
arXiv:2609.31864v1 Announce Type: cross Abstract: This paper presents AirLog, a smartphone-based life journaling system that automatically reconstructs users' store visits in shopping malls and summarizes them into human…
- arXiv cs.AIresearchDeep Reinforcement Learning for Equity Trading: Benchmarking Actor-Critic Methods with Forward Retraining
arXiv:2609.31870v1 Announce Type: cross Abstract: Consistently profitable trading is difficult because equity markets are noisy, non-stationary, and only partially predictable from historical data. We benchmark five deep…
- arXiv cs.AIresearchA Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
arXiv:2609.31877v2 Announce Type: replace-cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. F…
- arXiv cs.AIresearchDOHF: Online Diffusion Fine-tuning with Doob's $h$-transform Guidance
arXiv:2609.31882v2 Announce Type: replace-cross Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to estimate. In this work, w…
- arXiv cs.AIresearchFARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization
arXiv:2609.31890v1 Announce Type: cross Abstract: Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations and the need to p…
- arXiv cs.AIresearchNVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech
arXiv:2609.31892v1 Announce Type: cross Abstract: While modern text-to-speech (TTS) systems generate highly natural speech and support inline non-verbal vocalization (NVV) tags, accurate control over these events remains…
- arXiv cs.AIresearchAuditing Quality Filters for Long-Tail Human Data Curation
arXiv:2609.31896v1 Announce Type: cross Abstract: Robots on construction sites must detect workers who are kneeling or bending, which we call low poses. These workers can be lost from training datasets during automatic l…
- arXiv cs.AIresearchUnderstanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training
arXiv:2609.31900v1 Announce Type: cross Abstract: Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage p…
- arXiv cs.AIresearchROTE: Benchmarking Neural Memorization on Complexity-Controlled Symbolic Sequences
arXiv:2609.31918v1 Announce Type: cross Abstract: We introduce ROTE (RollOut Testing of Exact memorization), a benchmarking protocol for evaluating symbolic memorization of neural architectures. We study memorization and…
- arXiv cs.AIresearchSNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression
arXiv:2609.31965v1 Announce Type: cross Abstract: Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Sy…
- arXiv cs.AIresearchExtraction of clinical findings from mammography and breast ultrasound reports: a comparison between specialists and Artificial Intelligence
arXiv:2609.31974v1 Announce Type: cross Abstract: Breast cancer is the leading cause of cancer-related death among women in Brazil, and the time between the request and the release of mammography reports directly influen…
- arXiv cs.AIresearchCommunication between Frozen Large Language Models via Prompt Optimization in a Referential Game
arXiv:2609.31989v1 Announce Type: cross Abstract: We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoints. The two play a…
- arXiv cs.AIresearchVC Dimension and Expressivity of Real-Valued Transformers
arXiv:2609.31999v1 Announce Type: cross Abstract: Whereas previous results on abilities and limitations of transformers have restricted the definition of transformers in various ways, here we study softmax-attention, mul…