AI研究论文每日精选

UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities

ReasonIR: Training Retrievers for Reasoning Tasks

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Certified Mitigation of Worst-Case LLM Copyright Infringement

TesserAct: Learning 4D Embodied World Models

YoChameleon: Personalized Vision and Language Generation