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
RECON: Benchmarking Agent Memory for Compositional Reasoning over Long Contexts
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
Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection
arXiv cs.AI Research & Papers
LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Mode…
arXiv cs.AI Research & Papers
Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence
arXiv cs.AI Research & Papers
Generalist AI Control: Towards Multi-purpose Adaptive Algorithms
arXiv cs.AI Research & Papers
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
arXiv cs.AI Research & Papers
Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers
arXiv cs.AI Research & Papers
Accurate and Efficient Long-Term Memory for LLM Agents
arXiv cs.AI Research & Papers
A Survey on the Verification of Reinforcement Learning Policies
arXiv cs.AI Research & Papers
Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning
arXiv cs.AI Research & Papers
ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG
arXiv cs.AI Research & Papers
PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Covera…
arXiv cs.AI Research & Papers
It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches
arXiv cs.AI Research & Papers
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Age…
arXiv cs.AI Research & Papers
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Aut…
arXiv cs.AI Research & Papers
CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning
arXiv cs.AI Security & Safety
Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video G…
arXiv cs.AI Research & Papers
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Kno…
arXiv cs.AI Research & Papers
Distilled Reinforcement Learning for LLM Post-training
arXiv cs.AI Research & Papers
A Large-Scale Measurement of AI Bill of Materials Completeness in Hugging Face Models
arXiv cs.AI Research & Papers
Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI
arXiv cs.AI Research & Papers
Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism …
arXiv cs.AI Research & Papers
Talaria: Session-Aware Serverless Serving of Hundred-Billion-Parameter LLMs
arXiv cs.AI Research & Papers
DADIR: Density-Aware Data-level Imbalanced Regression Framework
arXiv cs.AI Research & Papers
CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation
arXiv cs.AI Research & Papers
Stress Testing Concept Erasure with Large Language Model Agents
arXiv cs.AI Research & Papers
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models
arXiv cs.AI Research & Papers
A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code Agents
arXiv cs.AI Research & Papers
Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computat…