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
No Gaussian Required: Contrastive Inverse Dynamics for JEPA World Models
arXiv cs.AI Research & Papers
Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Ta…
arXiv cs.AI Research & Papers
MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Asses…
arXiv cs.AI Research & Papers
CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
arXiv cs.AI Research & Papers
MoNe: Modular Neural Memory for Efficient Long Context Inference
arXiv cs.AI Research & Papers
Leveraging generative hallucination and biophysics-informed modeling for unified biomolec…
arXiv cs.AI Research & Papers
Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-B…
arXiv cs.AI Research & Papers
ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback
arXiv cs.AI Research & Papers
MoFE: A Novel Mixture-of-Experts Framework with Fourier Neural Operators for Cryptocurren…
arXiv cs.AI Research & Papers
NeuroAbs: A Neuro-Symbolic RTL Abstraction Framework for Property Checking Acceleration
arXiv cs.AI Research & Papers
Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems
arXiv cs.AI Research & Papers
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
arXiv cs.AI Research & Papers
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
arXiv cs.AI Research & Papers
Structural Plan-to-Model Conversion with Deterministic Geometry and Guarded Agentic Visio…
arXiv cs.AI Research & Papers
Adaptive surrogate modeling for high-dimensional spatio-temporal output
arXiv cs.AI Research & Papers
When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling
arXiv cs.AI Research & Papers
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
arXiv cs.AI Research & Papers
Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
arXiv cs.AI Research & Papers
Towards Zero-Shot Task Transfer with Neurosymbolic World Models
arXiv cs.AI Research & Papers
Teach and Grow: An Agent-Centered Architecture for General Robot Learning
arXiv cs.AI Security & Safety
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evi…
arXiv cs.AI Developer Tooling
Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories
arXiv cs.AI Research & Papers
Expected free energy as an information constraint on the Bethe Lagrangian
arXiv cs.AI Security & Safety
Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Me…
arXiv cs.AI Research & Papers
Token Optimization and Context Window Management in Multi-Agent AI Workflows
arXiv cs.AI Research & Papers
Q-Learning With World Models
arXiv cs.AI Research & Papers
From Abductive Explanations to Global Logical Rules for Node Classification in SGCs
arXiv cs.AI Research & Papers
Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functions
arXiv cs.AI Research & Papers
A Framework for Using and Evaluating LLMs as Surrogate Experts in Security Surveys: Relia…
arXiv cs.AI Research & Papers
Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable…