Español

Explorar

Noticias de IA

27413 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
RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents
arXiv cs.AI Research & Papers
Strategic Buying Agents
arXiv cs.AI Research & Papers
ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents
arXiv cs.AI Research & Papers
Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embod…
arXiv cs.AI Research & Papers
Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Sche…
arXiv cs.AI Research & Papers
Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving
arXiv cs.AI Research & Papers
MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding
arXiv cs.AI Research & Papers
Pooling-Based Context Modeling for Convolution-Free Deep Image Prior
arXiv cs.AI Research & Papers
Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diag…
arXiv cs.AI Research & Papers
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
arXiv cs.AI Research & Papers
G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Caus…
arXiv cs.AI Research & Papers
The Foreign Policy AI Evaluation Gap
arXiv cs.AI Research & Papers
LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection
arXiv cs.AI Research & Papers
TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models
arXiv cs.AI Research & Papers
LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering
arXiv cs.AI Research & Papers
STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
arXiv cs.AI Research & Papers
Individual Parameters in Weight-Sparse Transformers Appear Interpretable
arXiv cs.AI Research & Papers
HaorFloodAlert: A 72-Hour Machine Learning Early Warning System for Flash Floods in Bangl…
arXiv cs.AI Research & Papers
Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Lev…
arXiv cs.AI Research & Papers
Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption
arXiv cs.AI Research & Papers
Explainable Novel Category Discovery in Semantic Concept Space
arXiv cs.AI Research & Papers
Enhanced Feature Extraction for IoT Network Intrusion Detection Using GNNs and KAN
arXiv cs.AI Research & Papers
Auto: The AGI Compiler
arXiv cs.AI Research & Papers
CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Mod…
arXiv cs.AI Research & Papers
Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Ir…
arXiv cs.AI Research & Papers
PosterHarness: Turning Scientific Poster Generation into an Auditable Instruction-Followi…
arXiv cs.AI Research & Papers
Toward Efficient Agents: Memory, Tool learning, and Planning
arXiv cs.AI Research & Papers
Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous…
arXiv cs.AI Research & Papers
Language Models Represent and Transform Concepts with Shared Geometry
arXiv cs.AI Research & Papers
Transplanting, inverting, and preventing a misalignment persona: method-conditional emerg…