Yuxiao Dong

Associate Professor@Tsinghua University·中国·OpenReview

研究方向

large language models · pre-training models · LLMs · graph neural networks · graph embedding · graph representation learning · data mining · social network · computational social science

Yuxiao Dong

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents

MLE-RL: Reinforcement Learning for Self-Improvement in Machine Learning Agents

MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Scaling Speech-Text Pre-training with Synthetic Interleaved Data

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Controlling Large Language Model with Latent Action

Does RLHF Scale? Exploring the Effects of Data, Model, and Method

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

LVBench: An Extreme Long Video Understanding Benchmark

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA