Español

Explorar

Noticias de IA

22318 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
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
arXiv cs.AI Research & Papers
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Surviv…
arXiv cs.AI Research & Papers
Multimodal Reward Hacking in Reinforcement Learning
arXiv cs.AI Research & Papers
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
arXiv cs.AI Research & Papers
How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear…
arXiv cs.AI Research & Papers
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compress…
arXiv cs.AI Research & Papers
Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents o…
arXiv cs.AI Research & Papers
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distributio…
arXiv cs.AI Research & Papers
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv cs.AI Research & Papers
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Control…
arXiv cs.AI Research & Papers
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv cs.AI Research & Papers
A Formalization of the Mean-Field Derivation of the Vlasov Equation: AI-Assisted Lean For…
arXiv cs.AI Research & Papers
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
arXiv cs.AI Research & Papers
Projection Methods for Operator Learning and Universal Approximation
arXiv cs.AI Research & Papers
Tactile and Vision Conditioned Contact-Centric Control for Whole-Arm Manipulation
arXiv cs.AI Research & Papers
Interference and Retention in Continual Learning
arXiv cs.AI Research & Papers
Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM …
arXiv cs.AI Research & Papers
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusi…
arXiv cs.AI Research & Papers
Knowledge-Based Design Requirements for Generative Social Robots in Higher Education
arXiv cs.AI Research & Papers
Transition Matching Distillation for Fast Video Generation
arXiv cs.AI Research & Papers
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Lear…
arXiv cs.AI Research & Papers
RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches
arXiv cs.AI Research & Papers
Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
arXiv cs.AI Research & Papers
AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders
arXiv cs.AI Research & Papers
Contrastive Weak-to-strong Generalization
arXiv cs.AI Research & Papers
SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
arXiv cs.AI Research & Papers
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversa…
arXiv cs.AI Research & Papers
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
arXiv cs.AI Research & Papers
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
arXiv cs.AI Research & Papers
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement