Español

Explorar

Noticias de IA

30934 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 Security & Safety
Poison to Detect: Detection of Targeted Overfitting in Federated Learning
arXiv cs.AI Research & Papers
HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyb…
arXiv cs.AI Research & Papers
ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforce…
arXiv cs.AI Research & Papers
Understanding Reasoning from Pretraining to Post-Training
arXiv cs.AI Research & Papers
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
arXiv cs.AI Research & Papers
AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Condition…
arXiv cs.AI Research & Papers
Revisiting data-driven dynamic security assessment with a tabular foundation model
arXiv cs.AI Research & Papers
Frontier AI performance across the business disciplines: a case-grounded benchmark of kno…
arXiv cs.AI Research & Papers
When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry…
arXiv cs.AI Research & Papers
Why do CNNs excel at feature extraction? A mathematical explanation
arXiv cs.AI Research & Papers
CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning
arXiv cs.AI Research & Papers
SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction
arXiv cs.AI Research & Papers
Long-Context Fine-Tuning with Limited VRAM
arXiv cs.AI Research & Papers
From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Exp…
arXiv cs.AI Research & Papers
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
arXiv cs.AI Research & Papers
Candidate Attended Dialogue State Tracking Using BERT
arXiv cs.AI Research & Papers
Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve …
arXiv cs.AI Research & Papers
Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Age…
arXiv cs.AI Research & Papers
Orbis 2: A Hierarchical World Model for Driving
arXiv cs.AI Research & Papers
IMBench: A Benchmark for Intuitive Robotic Manipulation
arXiv cs.AI Research & Papers
When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizati…
arXiv cs.AI Research & Papers
Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge
arXiv cs.AI Research & Papers
Information-Directed Sampling for Causal Bandits
arXiv cs.AI Research & Papers
Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
arXiv cs.AI Research & Papers
Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding
arXiv cs.AI Research & Papers
LVSum: A Benchmark for Timestamp-Aware Long Video Summarization
arXiv cs.AI Research & Papers
On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous L…
arXiv cs.AI Research & Papers
Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly D…
arXiv cs.AI Research & Papers
Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario…
arXiv cs.AI Research & Papers
CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tu…