Español

Explorar

Noticias de IA

21031 elementos — filtrados, clasificados y sin duplicados

Todos 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
Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in P…
arXiv cs.AI Research & Papers
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libr…
arXiv cs.AI Research & Papers
A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just…
arXiv cs.AI Research & Papers
ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Trai…
arXiv cs.AI Research & Papers
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
arXiv cs.AI Research & Papers
Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Systematic Review and…
arXiv cs.AI Research & Papers
A World Model of Radiologist Reading for Medical Image Representation Learning
arXiv cs.AI Research & Papers
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation an…
arXiv cs.AI Research & Papers
Treatment Effect Estimation with Differentiated Networked Effect on Graph Data
arXiv cs.AI Research & Papers
{\Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation
arXiv cs.AI Research & Papers
Code2UML: Agentic LLMs with context engineering for scalable software visualization
arXiv cs.AI Research & Papers
AI-Driven Controlled Environment Agriculture as Resilient Infrastructure for U.S. Fresh-P…
arXiv cs.AI Research & Papers
Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footpri…
arXiv cs.AI Research & Papers
EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting…
arXiv cs.AI Research & Papers
Authority Signals in Claude AI Health Citations: A Descriptive Analysis Using the Authori…
arXiv cs.AI Research & Papers
TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling
arXiv cs.AI Research & Papers
E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology
arXiv cs.AI Research & Papers
L2IR: Revealing Latent Intent in Graph Fraud Detection
arXiv cs.AI Research & Papers
Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free …
arXiv cs.AI Research & Papers
LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation
arXiv cs.AI Research & Papers
Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation
arXiv cs.AI Research & Papers
MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
arXiv cs.AI Research & Papers
FoodMonitor: Benchmarking MLLMs for Explainable Compliance Analysis
arXiv cs.AI Research & Papers
SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompres…
arXiv cs.AI Research & Papers
PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training
arXiv cs.AI Research & Papers
Agent-Centric Social Trajectory Prediction: A Free Energy Principle Perspective
arXiv cs.AI Research & Papers
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
arXiv cs.AI Research & Papers
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
arXiv cs.AI Research & Papers
ADMFormer: An Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attenti…
arXiv cs.AI Research & Papers
CyBOKClaw: Human-in-the-Loop CyBOK Mapping for Cybersecurity Curriculum