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
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement
arXiv cs.AI Research & Papers
Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference
arXiv cs.AI Research & Papers
MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends
arXiv cs.AI Research & Papers
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
arXiv cs.AI Research & Papers
SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
arXiv cs.AI Research & Papers
Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy
arXiv cs.AI Research & Papers
From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small La…
arXiv cs.AI Research & Papers
Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defens…
arXiv cs.AI Research & Papers
Coverage Aware Active Evaluation for Failure Discovery with Paired Systems
arXiv cs.AI Research & Papers
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
arXiv cs.AI Research & Papers
How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generatin…
arXiv cs.AI Research & Papers
Exploring ESC Winners with Nested Diagrams
arXiv cs.AI Research & Papers
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
arXiv cs.AI Research & Papers
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation o…
arXiv cs.AI Research & Papers
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
arXiv cs.AI Research & Papers
FLARE MCMC: Fidelity-based Layer-Adaptive REcursive proposals for MCMC
arXiv cs.AI Research & Papers
Reward Machines for Signal Temporal Logic
arXiv cs.AI Research & Papers
Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, a…
arXiv cs.AI Research & Papers
Active Perception for Embodied Disambiguation
arXiv cs.AI Research & Papers
No Universal Signal Predicts Sample-Level LLM Regression under Version Updates
arXiv cs.AI Research & Papers
SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise …
arXiv cs.AI Research & Papers
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert …
arXiv cs.AI Research & Papers
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
arXiv cs.AI Research & Papers
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
arXiv cs.AI Research & Papers
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
arXiv cs.AI Research & Papers
NEURON: A Neuro-symbolic System for Grounded Clinical Explainability
arXiv cs.AI Research & Papers
AI Evaluation Should Work With Humans
arXiv cs.AI Research & Papers
Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through …
arXiv cs.AI Research & Papers
Measuring Cross-Task Behavioral Consistency in Language Model Agents
arXiv cs.AI Research & Papers
Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Proce…