Español

Explorar

Noticias de IA

37834 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
Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic …
arXiv cs.AI Research & Papers
PrimeAgentOrchestrator: Memory-Primed Agent Spawning for Personal AI Infrastructure
arXiv cs.AI Research & Papers
Interpretable Multimodal Classification with Linear Discriminant Tree Ensembles
arXiv cs.AI Research & Papers
FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
arXiv cs.AI Research & Papers
Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification
arXiv cs.AI Research & Papers
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
arXiv cs.AI Research & Papers
A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Ap…
arXiv cs.AI Research & Papers
Dual-Cache Latent Space Communication between Heterogeneous Language Models
arXiv cs.AI Research & Papers
Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills
arXiv cs.AI Research & Papers
Volumetric Radiology AI in the Era of Multimodal Large Language Models
arXiv cs.AI Research & Papers
Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their O…
arXiv cs.AI Research & Papers
RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation
arXiv cs.AI Research & Papers
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persis…
arXiv cs.AI Research & Papers
Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating L…
arXiv cs.AI Research & Papers
From Attention Masks to Inert Zero-Vector Tokens: OAttention and O-Closure for Token Dyna…
arXiv cs.AI Research & Papers
Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants
arXiv cs.AI Research & Papers
Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Pe…
arXiv cs.AI Research & Papers
An LLM agent for end-to-end computational materials discovery
arXiv cs.AI Research & Papers
Large Scale AI Grading of Handwritten Physics Assessments: Score Agreement and Olympiad T…
arXiv cs.AI Research & Papers
JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality J…
arXiv cs.AI Research & Papers
RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction
arXiv cs.AI Research & Papers
Difficulty-Aware Semantic-ID Optimization for Generative Recommendation
arXiv cs.AI Research & Papers
SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers
arXiv cs.AI Research & Papers
Edge-Based Agentic Retrieval-Augmented Generation for Autonomous FHWA Bridge Inspection C…
arXiv cs.AI Research & Papers
Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generat…
arXiv cs.AI Research & Papers
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
arXiv cs.AI Research & Papers
ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale…
arXiv cs.AI Research & Papers
One Hierarchy, Two Systems: Semantic Product IDs for Discovery-Surface Ranking and Search…
arXiv cs.AI Research & Papers
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
arXiv cs.AI Security & Safety
Vis-Poison: Poisoning Visual Knowledge in Multimodal Retrieval-Augmented Generation