English

Browse

AI News

30934 items — filtered, classified, deduplicated

All Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection
arXiv cs.AI Research & Papers
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
arXiv cs.AI Research & Papers
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
arXiv cs.AI Research & Papers
Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorit…
arXiv cs.AI Research & Papers
Catching MRI outliers: unsupervised detection and localization of MRI artefacts and clini…
arXiv cs.AI Security & Safety
AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Syste…
arXiv cs.AI Research & Papers
PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajecto…
arXiv cs.AI Research & Papers
TRAFA: Anticipating User Actions to Reduce Errors in Procedural Tasks with Predictive Fee…
arXiv cs.AI Research & Papers
Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Trans…
arXiv cs.AI Security & Safety
Batch Normalization Amplifies Memorization and Privacy Risks
arXiv cs.AI Research & Papers
Momentum Streams for Optimizer-Inspired Transformers
arXiv cs.AI Research & Papers
MX-SAFE: Versatile Inference- and Training-Proof Microscaling Format with On-the-Fly Expo…
arXiv cs.AI Research & Papers
ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale
arXiv cs.AI Security & Safety
Concept Drift Adaptation Using Self-Supervised and Reinforcement Learning In Android Malw…
arXiv cs.AI Research & Papers
Improving Labeling Consistency with Detailed Constitutional Definitions and AI-Driven Eva…
arXiv cs.AI Research & Papers
Action with Visual Primitives
arXiv cs.AI Research & Papers
Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
arXiv cs.AI Research & Papers
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activ…
arXiv cs.AI Research & Papers
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
arXiv cs.AI Research & Papers
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Le…
arXiv cs.AI Research & Papers
Continual Speaker Identity Unlearning with Minimal Interference
arXiv cs.AI Research & Papers
EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting…
arXiv cs.AI Research & Papers
Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural …
arXiv cs.AI Research & Papers
Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Exp…
arXiv cs.AI Research & Papers
Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Exp…
arXiv cs.AI Research & Papers
OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Man…
arXiv cs.AI Research & Papers
vAttention: Verified Sparse Attention
arXiv cs.AI Research & Papers
Local MAP Sampling for Diffusion Models
arXiv cs.AI Research & Papers
Beyond Predefined Learning Objects: A Thinking-Learning Interaction Model for Up-to-Date …
arXiv cs.AI Research & Papers
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model