AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhere Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning
arXiv:2610.32951v1 Announce Type: cross Abstract: Reinforcement learning for large language models often uses separate systems for inference and training. Even with identical weights and BF16 tensors, implementation diff…
- arXiv cs.AIresearchDairySocialTwin: Auditing the video-to-graph evidence chain in cattle social networks
arXiv:2610.32989v1 Announce Type: cross Abstract: Video-derived social graphs can appear precise while inheriting uncertainty from detection, tracking, classification, and aggregation. We present DairySocialTwin, a graph…
- arXiv cs.AIresearchWhispering Wisely: Smart Subset Selection for ASR Fine-Tuning
arXiv:2610.32997v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) models such as OpenAIs Whisper have substantially improved speech recognition quality but remain expensive to fine-tune, especially whe…
- arXiv cs.AIresearchEntity-Aware Evaluation of OCR Systems for Historical Document Transcription
arXiv:2610.33004v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily…
- arXiv cs.AIresearchTraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models
arXiv:2610.33008v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) enable flexible generation through iterative masked denoising, but incur substantial inference cost because token representations…
- arXiv cs.AIresearchMerge-Based Vocabulary Extension Stalls at the Pre-Tokenizer: An English-Preserving Repair for Nepali, Tested in Continued Pretraining
arXiv:2610.33016v1 Announce Type: cross Abstract: Llama-3, Qwen3 and many other open LLMs pre-tokenize text with a regular expression whose word class admits only Unicode letters. Devanagari vowel signs are combining mar…
- arXiv cs.AIresearchMine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own
arXiv:2610.33020v1 Announce Type: cross Abstract: If your brain were connected directly to someone else's, would you still know which thoughts were yours? We build a functional version with two copies of one language mod…
- arXiv cs.AIresearchConceptizer: Next-Token Prediction Is Not All You Need
arXiv:2610.33027v1 Announce Type: cross Abstract: Next-token prediction (NTP) rewards only the token that occurs next, penalizing every alternative. But natural language often offers many ways to express the same meaning…
- arXiv cs.AIresearchFeature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics
arXiv:2610.33030v1 Announce Type: cross Abstract: Deep models are the usual choice for respiratory sound classification, but in clinics without GPUs or connectivity that choice carries a cost. We compare classical and de…
- arXiv cs.AIresearchA Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models
arXiv:2610.33036v2 Announce Type: replace-cross Abstract: Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbr…
- arXiv cs.AIresearchGMoE-FTI: A Universal Facial Template Inversion Method Adopting Genuine Mixture-of-Experts Mechanism
arXiv:2610.33055v1 Announce Type: cross Abstract: Face recognition systems have been ubiquitously deployed across daily scenarios. To protect user privacy, mainstream systems store facial templates rather than raw face i…
- arXiv cs.AIresearchAerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs
arXiv:2610.33056v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in the aerial domain, wher…
- arXiv cs.AIresearchDRA-SAM: Disagreement-Driven Referential Active SAM for Low-Altitude Drone Referring Segmentation
arXiv:2610.33057v1 Announce Type: cross Abstract: Referring segmentation in low-altitude drone imagery requires distinguishing small, visually similar instances under complex linguistic and spatial constraints. Global in…
- arXiv cs.AIresearchKDHNet: A Knowledge-Driven Hybrid Network for Limited-Calibration SSVEP Decoding
arXiv:2610.33058v1 Announce Type: cross Abstract: Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) achieve high information transfer rates but often require sufficient subject-specific…
- arXiv cs.AIresearchMOSAIC: Towards a Universal Latent Space for Computational Pathology Foundation Models
arXiv:2610.33059v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) differ substantially in architecture, pretraining objective, training data and representation dimensionality, yet it remains unclear wh…
- arXiv cs.AIresearchMARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation
arXiv:2610.33060v1 Announce Type: cross Abstract: Generating an articulated object from images and text requires more than plausible parts and movable joints: the assembled mechanism must execute the intended motion. Thi…
- arXiv cs.AIresearchOddin: Latent Visual Reasoning in Unified Multimodal Models via Self-Distillation from Image Generation
arXiv:2610.33062v1 Announce Type: cross Abstract: Unified large multimodal models (ULMMs) are able to perform visual reasoning through interleaved text-image generation, but generating explicit intermediate images incurs…
- arXiv cs.AIresearchA Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures
arXiv:2610.33063v1 Announce Type: cross Abstract: Deployed vision models auto-accept confident predictions, so high-confidence errors propagate silently. Maximum Softmax Probability (MSP), the standard failure predictor,…
- arXiv cs.AIresearchProtoEEG: Structured Prototype Alignment for EEG Visual Decoding
arXiv:2610.33065v1 Announce Type: cross Abstract: EEG visual decoding remains difficult because scalp recordings are noisy, spatially coarse, and variable across trials and subjects. Most systems align each trial with a…
- arXiv cs.AIresearchPhaseBreak: Proactive Temporal Protection against Unauthorized Image-to-Video Animation
arXiv:2610.33070v1 Announce Type: cross Abstract: Image-to-Video (I2V) diffusion models can animate a single portrait or photograph, enabling shared images to be repurposed for motion synthesis without the subject's auth…
- arXiv cs.AIresearchVLMProbe: An Open-source Library for VLM Probing and Interpretation
arXiv:2610.33072v1 Announce Type: cross Abstract: Understanding how vision-language models use visual information requires connecting internal representations to model behavior. We present vlmprobe, an open-source librar…
- arXiv cs.AIresearchAGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models
arXiv:2610.33074v1 Announce Type: cross Abstract: Vision-language-action (VLA) models enable robots to perform tasks specified through natural-language instructions, but their large weight footprint challenges deployment…
- arXiv cs.AIresearchDiagnosing and Mitigating Evidence Misgrounding in Multimodal Knowledge Editing
arXiv:2610.33075v1 Announce Type: cross Abstract: Multimodal knowledge editing aims to update visually grounded facts in Multimodal Large Language Models (MLLMs) while preserving unrelated text and visual behaviors. Howe…
- arXiv cs.AIresearchEvaluating Visual Language Models on Visual Grounding for Visually Impaired People
arXiv:2610.33078v2 Announce Type: replace-cross Abstract: Visual grounding (VG) in visual question answering (VQA) is a fundamental capability of Vision-Language Models (VLMs), enabling the detection of the most relevant…
- arXiv cs.AIresearchAnalogPortBench: Benchmarking LLMs on Analog Circuit Porting
arXiv:2610.33088v1 Announce Type: cross Abstract: Analog circuit design still relies heavily on expert knowledge, and porting proven designs to new process nodes is a recurring bottleneck. As a lower supply reduces avail…
- arXiv cs.AIresearchBeyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries
arXiv:2610.33094v1 Announce Type: cross Abstract: Formal languages are widely used in software engineering to specify and verify program properties. Because their mathematical notation and logic are hard to read, develop…
- arXiv cs.AIresearchEGGPlacer: Energy-Guided Generative Chip Placement with Diffusion Models
arXiv:2610.33099v1 Announce Type: cross Abstract: Chip placement strongly affects routed wirelength and thermal behavior, yet these downstream metrics are difficult to evaluate during macro placement. Learning-based macr…
- arXiv cs.AIresearchWhale You Go Green? Immediate and Longitudinal Effects of Embodied Conversational AI Avatars on Sustainable Behavioral Tendencies and Pro-Environmental Attitudes
arXiv:2610.33191v1 Announce Type: cross Abstract: Embodied conversational AI can be persuasive, but can it motivate people to develop sustainable behavioral tendencies and increase pro-environmental attitudes? We conduct…
- arXiv cs.AIresearchImage Clustering with Vision-Language Model Embeddings
arXiv:2610.33265v1 Announce Type: cross Abstract: Pretrained vision-language models provide image representations whose suitability for clustering may vary with feature extraction, image domain, and partitioning algorith…
- arXiv cs.AIresearchThe As-If Machine: Personalized counterfactuals make distant policy risks feel close
arXiv:2610.33301v1 Announce Type: cross Abstract: Life experiences can shape policy attitudes, but we only live one life. Citizens may therefore fail to support policies addressing risks they have never personally experi…
- arXiv cs.AIresearchExploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns
arXiv:2610.33310v1 Announce Type: cross Abstract: Powder X-ray diffraction (XRD) is the primary high-throughput method for resolving crystal structures, a cornerstone of materials science. As high-throughput synthesis an…
- arXiv cs.AIresearchWhen Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training
arXiv:2610.33311v1 Announce Type: cross Abstract: How does pre-trained model capacity relate to performance after adaptation for causal tasks? We study two systems built on the Qwen 2.5 family: CausalLLM, which estimates…
- arXiv cs.AIresearchFrom Hype to ROI: An Economic Model for LLM Adoption in Information Systems and Security Operations
arXiv:2610.33352v1 Announce Type: cross Abstract: Large Language Models (LLMs) promise significant efficiency gains across information-intensive operations by automating repetitive language-based tasks. However, adoption…
- arXiv cs.AIresearchMOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search
arXiv:2610.33358v1 Announce Type: cross Abstract: Hardware-aware neural architecture search (NAS) requires jointly optimizing predictive accuracy and device-specific latency over discrete search spaces. While multi-objec…
- arXiv cs.AIresearchExact Unlearning After Data Curation
arXiv:2610.33426v1 Announce Type: cross Abstract: Training pipelines often remove similar examples before fitting a model. Deleting a raw record can change that selection and admit an example that was excluded before. Wh…
- arXiv cs.AIresearchQuantifying Meaning with SCAPE-T: Semantic Complexity from Encoder-Only Transformer Attention
arXiv:2610.33441v1 Announce Type: cross Abstract: Automated semantic complexity estimation remains underexplored in NLP, despite important applications in linguistics and interpretability. This paper defines semantic com…
- arXiv cs.AIresearchLLMs in Cloud: A Discussion on Architecture, Orchestration, and Inference
arXiv:2610.33475v1 Announce Type: cross Abstract: The widespread deployment of foundational Large Language Models (LLM) across cloud datacenters marks a fundamental paradigm shift from stateless deep learning toward dist…
- arXiv cs.AIresearchA Unified Analysis of Importance-Corrected Momentum Actor-Critic over a Markovian Trajectory
arXiv:2610.33477v1 Announce Type: cross Abstract: We present a generic actor-critic method that combines a ridge-regularized pathwise least-squares temporal-difference (LSTD) critic with importance-corrected momentum (IC…
- arXiv cs.AIresearchMarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding
arXiv:2610.33478v2 Announce Type: replace-cross Abstract: Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, including the…
- arXiv cs.AIresearchEnergy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model
arXiv:2610.33479v1 Announce Type: cross Abstract: Lung tumor segmentation plays a vital role in early detection and treatment planning of lung cancer. Although state-of-the-art deep learning models achieve high dice scor…
- arXiv cs.AIresearchError-Subspace Calibration for Multi-Task Model Merging
arXiv:2610.33483v1 Announce Type: cross Abstract: Model merging combines task-specific expert models into a single model without joint training on their original datasets, but often incurs a performance gap relative to t…
- arXiv cs.AIresearchPacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
arXiv:2610.33525v1 Announce Type: cross Abstract: Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises significant privacy concerns that the raw client dat…
- arXiv cs.AIresearchSEDATE: Do Large Language Models Share an Aggression Circuit Across Languages?
arXiv:2610.33542v1 Announce Type: cross Abstract: As the applications of AI continue to expand across various multimodal and multilingual domains, ensuring safe and responsible deployment of these systems has become an i…
- arXiv cs.AIresearchHybrid-time PINNs: Discontinuity-Aware Physics-Informed Neural Networks for Learning Hybrid Dynamical Systems
arXiv:2610.33562v1 Announce Type: cross Abstract: Hybrid dynamical systems flow continuously but jump at discrete events. Physics-informed neural networks (PINNs) fit data while enforcing known dynamics, but a single net…
- arXiv cs.AIresearchWorldFailBench: Do World Models Understand Policy Failures?
arXiv:2610.33565v1 Announce Type: cross Abstract: Robot policy evaluation informs deployment decisions and policy improvement, but physical testing and simulator preparation require substantial effort. World models offer…
- arXiv cs.AIresearchMycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities
arXiv:2610.33608v1 Announce Type: cross Abstract: Hallucination detection is increasingly important for evaluating and deploying large language models. However, existing methods are often compared across benchmarks that…
- arXiv cs.AIresearchDROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions
arXiv:2610.33635v1 Announce Type: cross Abstract: Pavement crack segmentation under low light is degraded by reduced contrast, shadows, headlight glare, joints, stains, and wet seams. Existing crack segmentation methods…
- arXiv cs.AIresearchExtraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network
arXiv:2610.33671v1 Announce Type: cross Abstract: We study fully connected neural-network reconstruction by combining cryptanalytic weight-direction extraction with learning from predicted labels. We adapt a ReLU extract…
- arXiv cs.AIresearchEmbedding-Based Educational Taxonomies
arXiv:2610.33694v1 Announce Type: cross Abstract: Educational taxonomies organize educational content, such as exercise problems, into concepts, which are also called skills or knowledge components. These taxonomies defi…
- arXiv cs.AIresearchE3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges
arXiv:2610.33704v1 Announce Type: cross Abstract: Depth boundaries remain a major source of error in stereo matching. For IGEV on Scene Flow, geometric edge pixels account for only 6% of evaluated pixels but about half o…