Español

Explorar

Noticias de IA

29349 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
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
arXiv cs.AI Research & Papers
Hardware Design and Security in the Era of Chiplets and LLMs
arXiv cs.AI Research & Papers
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation fo…
arXiv cs.AI Research & Papers
Reconstructing Persistent Worlds from Narratives for Narrative-Grounded Interactive Exper…
arXiv cs.AI Research & Papers
Calibrating Transformer Attention via Task-Space Sensitivity Feedback
arXiv cs.AI Research & Papers
NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Le…
arXiv cs.AI Research & Papers
CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers
arXiv cs.AI Research & Papers
Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings
arXiv cs.AI Research & Papers
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LL…
arXiv cs.AI Research & Papers
FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents
arXiv cs.AI Research & Papers
MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres
arXiv cs.AI Research & Papers
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
arXiv cs.AI Research & Papers
Stabilizing Multi-Attack Adversarial Training via Bandit Optimization
arXiv cs.AI Research & Papers
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
arXiv cs.AI Research & Papers
FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Profe…
arXiv cs.AI Research & Papers
The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissocia…
arXiv cs.AI Research & Papers
MediRec: Enhancing Chinese Medication Recommendation with Explainable Clinical Reasoning
arXiv cs.AI Research & Papers
Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecasting
arXiv cs.AI Research & Papers
Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
arXiv cs.AI Research & Papers
Text2GraphQuery-Bench: A Text to Graph Query Benchmark
arXiv cs.AI Research & Papers
Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits
arXiv cs.AI Research & Papers
Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theore…
arXiv cs.AI Research & Papers
Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections
arXiv cs.AI Research & Papers
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answe…
arXiv cs.AI Research & Papers
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
arXiv cs.AI Research & Papers
Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation
arXiv cs.AI Research & Papers
Design Choices That Matter: A Functional ANOVA Analysis for Remote Sensing Multi-Label Cl…
arXiv cs.AI Research & Papers
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
arXiv cs.AI Research & Papers
AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering
arXiv cs.AI Research & Papers
Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Att…