Yongyuan Liang
Yongyuan (Cheryl) Liang's research focuses on developing foundation models and intelligent agents.
She actively explores both theoretical frameworks and empirical findings, with specific research interests in:
Foundation models : Large multi-modal models/generative models for agentic tasks in digital and physical environments.
Alignment : Post-training alignment for human values and preferences with reasoning and planning.
Trustworthy AI : Building robust and reliable AI agents for decision-making.
I join UMD CS as a PhD student, advised by Furong Huang and also work closely with Huazhe Xu (IIIS) .
I received my B.S. degree in Mathematics from Sun Yat-sen University, developing my interests in Stochastic Process and Game Theory.
I'm always happy to collaborate with graduate/undergraduate students. Please drop me an email if you'd like to have a (virtual) coffee chat :)
I'm looking for part-time/full-time internship opportunities . Feel free to reach out if you're interested in my research.
News
Oct' 24  
Make-An-Agent has been selected as an oral presentation in NeurIPS 2024 AFM Workshop .
Sept' 24  
Make-An-Agent will appear in NeurIPS 2024.
June' 24  
ACE has been selected as a long oral presentation in ICML 2024.
May' 24  
Two papers to appear in ICML 2024.
Feb' 24  
Have been awarded a Dean’s Fellowship.
Jan' 24  
Three papers to appear in ICLR 2024, including two spotlights and one poster.
Selected Publications & Preprints
* denotes equal contributions ; † indicates equal advising.
Foundation Model
Robots Pre-Train Robots: Manipulation- Centric Robotic Representation from Large- Scale Robot Datasets
Guangqi Jiang*, Yifei Sun*, Tao Huang*, Huanyu Li, Yongyuan Liang †, Huazhe Xu†
arXiv , 2024
Project Page  / 
Paper  / 
Code  / 
Models  / 
Twitter
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Yongyuan Liang , Tingqiang Xu, Kaizhe Hu, Guangqi Jiang, Furong Huang, Huazhe Xu
NeurIPS , 2024
NeurIPS Workshop AFM , 2024 (Oral Talks - Top 3%)
Project Page  / 
Paper  / 
Code  / 
Models & Dataset  / 
Twitter
PREMIER-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Ruijie Zheng, Yongyuan Liang , Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Basu, Furong Huang
ICML , 2024
NeurIPS Workshop FMDM , 2023
Project Page  / 
Paper  / 
Code  / 
Twitter
Decision-making
ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Tianying Ji*, Yongyuan Liang* , Yan Zeng, Yu Luo, Guowei Xu, Jiawei Guo, Ruijie Zheng, Furong Huang, Fuchun Sun, Huazhe Xu
ICML , 2024 (Oral - Top 1.5%)
Project Page  / 
Paper  / 
Code  / 
Twitter
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Guowei Xu*, Ruijie Zheng*, Yongyuan Liang* ,
Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu
ICLR , 2024 (Spotlight - Top 5%)
CORL Workshop PRL , 2023
Project Page  / 
Paper  / 
Code  / 
Twitter
Trustworthy AI
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Yongyuan Liang , Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Benjamin Eysenbach, Tuomas Sandholm, Furong Huang, Stephen Marcus McAleer
ICLR , 2024
ICML Workshop AdvML-Frontiers , 2023
Paper  / 
Code  / 
Twitter
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Yongyuan Liang* , Yanchao Sun*, Ruijie Zheng, Furong Huang
NeurIPS , 2022
NeurIPS Workshop SafeRL , 2021 (Spotlight Talks)
Paper  / 
Code  / 
Slides
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang , Furong Huang
arXiv , 2024
ICML Workshop on Models of Human Feedback for AI Alignment , 2024
Paper  / 
Code
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Xiangyu Liu*, Chenghao Deng*, Yanchao Sun, Yongyuan Liang , Furong Huang
ICLR , 2024 (Spotlight - Top 5%)
NeurIPS Workshop MASEC , 2023
Project Page  / 
Paper  / 
Code  / 
Twitter
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Yanchao Sun, Ruijie Zheng, Yongyuan Liang , Furong Huang
ICLR , 2022
NeurIPS Workshop SafeRL , 2021 (Best Paper Award)
Project Page  / 
Paper  / 
Code
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang , Soheil Feizi, Sumitra Ganesh, Furong Huang
ICLR , 2023
Paper  / 
Code
Professional Service
Conference Program Committee: ICML(2022-2024), NeurIPS(2021-2024), ICLR(2021-2025)
Workshop Program Committee: FMDM 2023 at NeurIPS
Misc
If my name is a bit tricky to pronounce for you, it is also great to call me Cheryl [ˈʃerəl].
I've been playing the violin🎻 for over 15 years and served as a principal violinist in the university orchestra.
Been a fan of Novak Djokovic since 2012.
My Erdős number = 4 .