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
LinTree: Improving LLM Reasoning with Explicitly Structured Search Histories
arXiv cs.AI Research & Papers
Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies
arXiv cs.AI Research & Papers
Reinterpreting Safety Thresholds as Neuron Spiking Thresholds
arXiv cs.AI Research & Papers
Structured interactions improve distributed coordination beyond model scaling in a real-w…
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
Social welfare optimisation under institutional reward and punishment
arXiv cs.AI Research & Papers
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control …
arXiv cs.AI Research & Papers
Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
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
Simulation of collision avoidance behavior in crowd movement by data-driven approach
arXiv cs.AI Research & Papers
Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models
arXiv cs.AI Research & Papers
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
arXiv cs.AI Security & Safety
Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
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
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
arXiv cs.AI Research & Papers
MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulati…
arXiv cs.AI Research & Papers
Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Control…
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
Towards Atoms of Large Language Models