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
Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Lea…
arXiv cs.AI Research & Papers
How Formerly Incarcerated People Envision Technologies for Prison Parole
arXiv cs.AI Research & Papers
When to Use Which? Benchmarking Optimisers for Configurable Systems under Varying Budgets
arXiv cs.AI Research & Papers
Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evid…
arXiv cs.AI Research & Papers
Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent
arXiv cs.AI Research & Papers
Fantastic Adaptive Taxonomies and How to Use Them
arXiv cs.AI Research & Papers
A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-…
arXiv cs.AI Research & Papers
DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification
arXiv cs.AI Research & Papers
GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with…
arXiv cs.AI Research & Papers
Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architec…
arXiv cs.AI Research & Papers
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Age…
arXiv cs.AI Research & Papers
It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches
arXiv cs.AI Research & Papers
PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Covera…
arXiv cs.AI Research & Papers
DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross…
arXiv cs.AI Research & Papers
Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillati…
arXiv cs.AI Research & Papers
ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG
arXiv cs.AI Research & Papers
Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning
arXiv cs.AI Research & Papers
A Survey on the Verification of Reinforcement Learning Policies
arXiv cs.AI Research & Papers
Accurate and Efficient Long-Term Memory for LLM Agents
arXiv cs.AI Research & Papers
Efficient EEG Seizure Detection Using INT8 Quantization, Channel Pruning, and Spiking Neu…
arXiv cs.AI Research & Papers
Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers
arXiv cs.AI Research & Papers
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
arXiv cs.AI Research & Papers
Generalist AI Control: Towards Multi-purpose Adaptive Algorithms
arXiv cs.AI Research & Papers
Emergent Hierarchical Monosemantic Neurons from the Group-Contrastive Forward-Forward Alg…
arXiv cs.AI Research & Papers
Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence
arXiv cs.AI Research & Papers
LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Mode…
arXiv cs.AI Research & Papers
GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
arXiv cs.AI Research & Papers
Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection
arXiv cs.AI Research & Papers
DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidan…
arXiv cs.AI Research & Papers
RECON: Benchmarking Agent Memory for Compositional Reasoning over Long Contexts