Español

Explorar

Noticias de IA

29670 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
NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
arXiv cs.AI Research & Papers
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
arXiv cs.AI Research & Papers
Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Au…
arXiv cs.AI Research & Papers
Structure-Induced Information for Rerooting Levin Tree Search
arXiv cs.AI Research & Papers
SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
arXiv cs.AI Research & Papers
Distilling LLM Feedback for Lean Theorem Proving
arXiv cs.AI Research & Papers
Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Ag…
arXiv cs.AI Research & Papers
Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Age…
arXiv cs.AI Research & Papers
G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition
arXiv cs.AI Research & Papers
Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAtte…
arXiv cs.AI Research & Papers
Weight Decay Improves Language Model Plasticity
arXiv cs.AI Research & Papers
CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabil…
arXiv cs.AI Research & Papers
CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects
arXiv cs.AI Research & Papers
MAECO-Lite: Modular Ontology for Dynamic Malware Analysis
arXiv cs.AI Research & Papers
SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs
arXiv cs.AI Research & Papers
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforc…
arXiv cs.AI Research & Papers
Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
arXiv cs.AI Research & Papers
AMix-2: Establishing Protein as a Native Modality in Large Language Models
arXiv cs.AI Research & Papers
Learning Cardiac Latent Representations in Vectorcardiogram Space
arXiv cs.AI Research & Papers
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
arXiv cs.AI Research & Papers
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical L…
arXiv cs.AI Research & Papers
The Terminal Representation in Reinforcement Learning
arXiv cs.AI Research & Papers
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
arXiv cs.AI Research & Papers
SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medica…
arXiv cs.AI Research & Papers
MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulati…
arXiv cs.AI Research & Papers
Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phr…
arXiv cs.AI Research & Papers
A Kinetic Energy Perspective of Flow Matching
arXiv cs.AI Research & Papers
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
arXiv cs.AI Research & Papers
Towards Atoms of Large Language Models
arXiv cs.AI Research & Papers
Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models