AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSubject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings
arXiv:2609.30832v1 Announce Type: cross Abstract: Perceived speech decoding based on non-invasive brain-computer interface (BCI) signals has been extensively studied in recent years. Research in this field primarily face…
- arXiv cs.AIresearchMOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
arXiv:2609.30837v2 Announce Type: replace-cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes each prompt to…
- arXiv cs.AIresearchPersistent Negatives for Adversarial Black-Box On-Policy Distillation
arXiv:2609.30864v1 Announce Type: cross Abstract: Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token probabilities. Advers…
- arXiv cs.AIresearchAdaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC
arXiv:2609.30891v1 Announce Type: cross Abstract: Semantic communication (SemCom) and integrated sensing and communication (ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied…
- arXiv cs.AIresearchRobust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations
arXiv:2609.30918v2 Announce Type: replace-cross Abstract: Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what the change…
- arXiv cs.AIresearchUltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound
arXiv:2609.30928v1 Announce Type: cross Abstract: Ultrasound is one of the most widely used medical imaging modalities, and recent large vision-language models(VLMs) have shown increasing capabilities in ultrasound image…
- arXiv cs.AIresearchEstimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
arXiv:2609.30935v1 Announce Type: cross Abstract: Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgettin…
- arXiv cs.AIresearchSpackle: Completing Large View Single Image NVS with Adaptive Gaussians
arXiv:2609.30941v1 Announce Type: cross Abstract: Single-image novel view synthesis (NVS) enables photorealistic rendering of un- observed viewpoints from a single input. Practical NVS systems require two key capabilitie…
- arXiv cs.AIresearchOneWorld: Learning Consistent Physics Across Actions in World Models
arXiv:2609.30946v1 Announce Type: cross Abstract: Action-conditioned video world models aim to predict scene evolution under different actions, a capability that is essential for reliable planning, decision-making, and i…
- arXiv cs.AIresearchPORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling Problem
arXiv:2609.30948v1 Announce Type: cross Abstract: The Job Shop Scheduling Problem (JSSP) is a fundamental combinatorial optimization problem in industrial optimization. This work introduces Pretrained Offline Reinforceme…
- arXiv cs.AIresearchMVVBench: Benchmarking 4D Reasoning in Vision-Language Models
arXiv:2609.30952v1 Announce Type: cross Abstract: Multi-view video understanding requires integrating spatial and temporal evidence across multiple, often non-overlapping camera streams: tracking entities as they transit…
- arXiv cs.AIresearchDoes Uniform Discrete Diffusion Need Time?
arXiv:2609.30977v1 Announce Type: cross Abstract: Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this paper, we first show t…
- arXiv cs.AIresearchFARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators
arXiv:2609.30982v1 Announce Type: cross Abstract: Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. Thi…
- arXiv cs.AIresearchFLIP: Final Layer Inference-Time Probing for Vision-Language Models
arXiv:2609.30993v2 Announce Type: replace-cross Abstract: We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in an open-weight vision-language model (VLM) supports st…
- arXiv cs.AIresearchThe Linear Representation Hypothesis for Vision-Language-Action Models
arXiv:2609.30996v2 Announce Type: replace-cross Abstract: The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on semantic information through the internal representations o…
- arXiv cs.AIresearchCan Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
arXiv:2609.30997v1 Announce Type: cross Abstract: Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. This becomes a robustne…
- arXiv cs.AIresearchG$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation
arXiv:2609.31009v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is a practical approach to reducing the memory and computational footprint of large language models (LLMs) without retraining. GPTQ-based…
- arXiv cs.AIresearchQuantum Diffusion Models for Medical Image Analysis
arXiv:2609.31070v1 Announce Type: cross Abstract: Quantum Machine Learning is a novel field of research aimed at devising machine learning approaches exploiting principles of quantum mechanics, such as superposition, ent…
- arXiv cs.AIresearchDepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models
arXiv:2609.31103v1 Announce Type: cross Abstract: Spatial reasoning with metric constraints requires linking objects to geometric measurements and preserving their numerical content during language reasoning. We present…
- arXiv cs.AIresearchBayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
arXiv:2609.31107v2 Announce Type: replace-cross Abstract: We study Bayesian optimization (BO) through the lens of information geometry. Pulling back the Fisher information metric through the surrogate posterior map yield…
- arXiv cs.AIresearchFrom Shortcut Learning to Discrete Neural Insertion Sort
arXiv:2609.31114v1 Announce Type: cross Abstract: Neural algorithmic reasoning aims to train neural networks to follow known algorithms and generalize beyond the input sizes seen during training. However, correct final o…
- arXiv cs.AIresearchPocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding
arXiv:2609.31135v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent methods achieve strong…
- arXiv cs.AIresearchJevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models
arXiv:2609.31142v2 Announce Type: replace-cross Abstract: Typed decision models (TDMs), such as Jev, answer a question about an input with a probability, an option, or an ordinal level. Web services execute these decisio…
- arXiv cs.AIresearchFedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification
arXiv:2609.31150v1 Announce Type: cross Abstract: Cross-site lung histopathology classification must account for stain variation, non-IID client data, missing classes, and the cost of adapting large pathology encoders. T…
- arXiv cs.AIresearchTeacher-Anchored Selection of Post-Training Quantized Models under Domain Shift
arXiv:2609.31155v1 Announce Type: cross Abstract: Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We study selection ove…
- arXiv cs.AIresearchReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation
arXiv:2609.31160v1 Announce Type: cross Abstract: Vessel segmentation in medical images is essential for many clinical tasks, ranging from diagnosis to treatment planning. However, it remains challenging due to complex v…
- arXiv cs.AIresearchSPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations
arXiv:2609.31164v1 Announce Type: cross Abstract: Recommender systems engineer serendipity to foster active exploration and break predictable consumption cycles. The problem with existing offline beyond-accuracy metrics…
- arXiv cs.AIresearchImproving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting
arXiv:2609.31169v1 Announce Type: cross Abstract: Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. While models, through m…
- arXiv cs.AIresearchBAT-CLIP: Trimodal Alignment of Brain, Audio and Text
arXiv:2609.31180v1 Announce Type: cross Abstract: Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces. However, current CL…
- arXiv cs.AIresearchRethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews
arXiv:2609.31191v1 Announce Type: cross Abstract: Data quality research has usually treated data as an input that is stored, processed, and validated. In AI-driven software-intensive systems, data also shapes model behav…
- arXiv cs.AIresearchAcoustic-to-Text KV Compression for Full-Duplex Speech Models
arXiv:2609.31224v1 Announce Type: cross Abstract: Full-duplex speech language models continuously accumulate acoustic key-value (KV) states, making long-running interactions memory-intensive. During listening, the model…
- arXiv cs.AIresearchGeometric Inconsistency Localization in Multi-View Image Sets
arXiv:2609.31247v1 Announce Type: cross Abstract: Novel view synthesis (NVS) models can produce realistic new views of the same scene from different viewpoints. However, these generated views are not always geometrically…
- arXiv cs.AIresearchMoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries
arXiv:2609.31261v1 Announce Type: cross Abstract: The quadratic complexity of dense self-attention remains a central bottleneck for long-context language modeling. Many efficient alternatives address this cost by decidin…
- arXiv cs.AIresearchSoftmax Reparameterization for Output-Head Quantization
arXiv:2609.31291v2 Announce Type: replace-cross Abstract: Large vocabularies make output heads a substantial inference cost in small language models. We introduce softmax reparameterization, a post-training method that s…
- arXiv cs.AIresearchUniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning
arXiv:2609.31298v2 Announce Type: replace-cross Abstract: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder for which early and accurate diagnosis is critical to improving long-term developmental ou…
- arXiv cs.AIresearchTowards VLA-Dreamer: Refining VLA Behavior Using World Models
arXiv:2609.31313v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs), while showing strong potential for robot control, require massive amounts of high-quality imitation learning data. Moreover, the abs…
- arXiv cs.AIresearchDyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models
arXiv:2609.31349v1 Announce Type: cross Abstract: Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive downstream use. Dis…
- arXiv cs.AIresearchHighlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
arXiv:2609.31382v1 Announce Type: cross Abstract: Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and…
- arXiv cs.AIresearchGuiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization
arXiv:2609.31383v1 Announce Type: cross Abstract: End-to-end driving policies are commonly trained through open-loop behavior cloning, yet they must ultimately operate in closed-loop when deployed on a vehicle, creating…
- arXiv cs.AIresearchIntent2Tc: Automated Intent-to-Traffic Control Translation with Language Models
arXiv:2609.31397v1 Announce Type: cross Abstract: Automated and highly usable Quality-of-Service (QoS) enforcement requires translating high-level service intents into deployable traffic-management policies. Although int…
- arXiv cs.AIresearchSorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers
arXiv:2609.31403v1 Announce Type: cross Abstract: Vision-language models (VLMs), despite their success in optical character recognition (OCR) tasks, are vulnerable to typographic attacks and have a fragile structure for…
- arXiv cs.AIresearchImplicit Neural Representation for Hyperspectral Video Compression
arXiv:2609.31435v1 Announce Type: cross Abstract: With the advent of snapshot cameras, hyperspectral video is becoming more readily available. In recent years, new applications have emerged which have led to increasingly…
- arXiv cs.AIresearchViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs
arXiv:2609.31448v1 Announce Type: cross Abstract: Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answering. Yet their langu…
- arXiv cs.AIresearchFrom Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training
arXiv:2609.31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objectives relate to imag…
- arXiv cs.AIresearchDifferent Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality
arXiv:2609.31454v1 Announce Type: cross Abstract: Federated learning (FL) data corruption can affect either inputs or labels, but it remains unclear whether input-conditional uncertainty and prediction-label loss expose…
- arXiv cs.AIresearchUncertainty-Aware Federated Learning for Infant Movement Analysis
arXiv:2609.31463v1 Announce Type: cross Abstract: Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automate…
- arXiv cs.AIresearchEvaluating Cultural Awareness of LLMs for Haitian Creole
arXiv:2609.31506v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit substantial performance disparities between high- and low-resource languages. Beyond lower task performance, they often fail to captu…
- arXiv cs.AIresearchClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
arXiv:2609.31509v1 Announce Type: cross Abstract: We present ClearGS for 3D Gaussian Splatting (3DGS) from handheld videos with uneven viewpoint coverage and mixed frame quality. Rather than selecting frames with binary…
- arXiv cs.AIresearchCan You Check That? The Checkability Boundary for Local LLM Network Automation
arXiv:2609.31540v1 Announce Type: cross Abstract: Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small l…
- arXiv cs.AIresearchAdapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum
arXiv:2609.31569v1 Announce Type: cross Abstract: Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not o…