About me

I am a CS PhD student at UIUC, advised by Prof. Tong Zhang and Prof. Huan Zhang. Previously, I earned my bachelor’s and master’s degrees from the Department of Automation at Tsinghua University and CSE, HKUST. Currently, my research focuses on: Agents, Trustworthy LLMs/VLMs, and Deep reinforcement learning.

Prior to my PhD, I was fortunate to work closely with Prof. Chongjie Zhang (Washington University in St. Louis), Dr. Lei Han (Tencent AI Lab), and Prof. Meng Fang (University of Liverpool).

News

• 🎉 (2025.9) GUI-Actor and ADG are accepted to NeurIPS 2025! MergeBench is accepted to the Datasets & Benchmarks Track! Congrats to all co-authors!
• 🎉 (2025.8) MiCRo is accepted to EMNLP 2025 main conference with award nomination!
• 🌟 (2025.6) We’ve released GUI-Actor, a novel GUI grounding model that combines an attention-based action head with a grounding verifier. Explore more on our project page!
• 💻 (2025.5) Starting my internship at Microsoft Research, Redmond.
• 🎉 (2025.5) Decomposed Reward Models (DRMs) is accepted to ACL 2025.
• 🎉 (2025.5) EmbodiedBench is accepted to ICML 2025 as an oral paper! Thanks to my co-authors!
• 🌟 (2025.02) We released EmbodiedBench, a new comprehensive and multifaceted benchmark for multimodal embodied agents. Check out our paper and project page.
• 🎉 (2025.1) Robust Decision Transformer and DynaMath are accepted by ICLR 2025! New versions will be updated soon.
• 🌟 (2024.10) A dynamic visual math benchmark is out! Check the project page and the DynaMath paper.
• 🎉 (2024.9) GRM is accepted by NeurIPS 2024! Check out our GRM series here.
• 🎉 (2024.5) Rewards-in-Context (RiC) is accepted by ICML 2024! Thanks to my co-authors!
• 🎉 (2024.1) Robust IQL is accepted by ICLR 2024 as a spotlight paper!

Selected Publications

Multimodal GUI Agent and Embodied Agent

• GUI-Actor: Attention-based Grounding with Verifiable Action Head for GUI Agents. Preprint 2025. [code] [website]
  Qianhui Wu$^*$, Kanzhi Cheng$^*$, Rui Yang$^*$, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao, Reuben Tan, Si Qin, Lars Liden, Qingwei Lin, Huan Zhang, Tong Zhang, Jianbing Zhang, Dongmei Zhang, Jianfeng Gao

• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents. ICML 2025 (Oral). [code] [website]
  Rui Yang$^*$, Hanyang Chen $^*$, Junyu Zhang $^*$, Mark Zhao $^*$, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang

Multimodal Math Reasoning

• DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models. ICLR 2025. [code] [website]
  Chengke Zou $^*$, Xingang Guo $^*$, Rui Yang $^*$, Junyu Zhang, Bin Hu, Huan Zhang.

ML for LLMs

• Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs. NeurIPS 2024. [code]
  Rui Yang, Ruomeng Ding, Yong Lin, Huan Zhang, Tong Zhang.

• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment. ICML 2024. [code]
  Rui Yang $^*$, Xiaoman Pan $^*$, Feng Luo $^*$, Shuang Qiu $^*$, Han Zhong, Dong Yu, Jianshu Chen.

• Rethinking Diverse Human Preference Learning through Principal Component Analysis. ACL 2025 (Findings).
  Feng Luo$^*$, Rui Yang$^*$, Hao Sun, Chunyuan Deng, Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen.

• MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning. EMNLP 2025 (Main).
  Jingyan Shen$^*$, Jiarui Yao$^*$, Rui Yang$^*$, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao.

Robust Offline RL

• Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling. ICLR 2025.
  Jiawei Xu $^*$, Rui Yang $^*$, Shuang Qiu, Feng Luo, Meng Fang, Baoxiang Wang, Lei Han.

• Towards Robust Offline Reinforcement Learning under Diverse Data Corruption. ICLR 2024. (Spotlight) [code]
  Rui Yang $^*$, Han Zhong $^*$, Jiawei Xu $^*$, Amy Zhang, Chongjie Zhang, Lei Han, Tong Zhang.

• Corruption-Robust Offline Reinforcement Learning with General Function Approximation. NeurIPS 2023. [code]
  Chenlu Ye $^*$, Rui Yang $^*$, Quanquan Gu, Tong Zhang.

• RORL: Robust Offline Reinforcement Learning via Conservative Smoothing. NeurIPS 2022. (Spotlight) [code]
  Rui Yang $^*$, Chenjia Bai $^*$, Xiaoteng Ma, Zhaoran Wang, Chongjie Zhang, Lei Han.

Goal-conditioned RL

• What Is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?. ICML 2023. [code]
  Rui Yang, Yong Lin, Xiaoteng Ma, Hao Hu, Chongjie Zhang, Tong Zhang.

• Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL. ICLR 2022. [code]
  Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, Chongjie Zhang.

Experiences

• Research Intern at Microsoft Research, 2025.

• Research Intern at Tencent AI Lab and Robotics X Lab, 2020-2022 (Multiple internship terms).

• ML Intern at Meituan Financial Service Group, 2019.

Services

Conference Reviewer: ICML, ICLR, NeurIPS ($\color{red}{\text{Top Reviewer}}$ in NeurIPS 2023), ACL/ARR, ICRA, AAMAS.

Journal Reviewer: IEEE Robotics and Automation Letters (RA-L), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Artificial Intelligence (TAI), Machine Learning, Journal of Artificial Intelligence Research.

Teaching Assistant: COMP 4211 Machine Learning, HKUST; COMP 1021 Introduction to Computer Science, HKUST

Hobbies

In my leisure time, I enjoy sports like running, table tennis, and swimming. During my time at Tsinghua University, I was an amateur long-distance runner. In 2019, I completed a half marathon (21.0975 km) in 1 h 30 min and a full marathon (42.195 km) in 3 h 36 min. However, since starting my PhD I haven’t had time for regular running training, so I’ve let it slide. Hopefully I’ll get a chance to update my record once I graduate🙂.