Yongyuan Cheryl Liang

My research focuses on developing large foundation models and agentic intelligence. I actively explore both theoretical frameworks and empirical findings, with specific research interests in:

Large Multimodal Models and World Models for general agentic tasks, including virtual and physical intelligence.
Post Training: Multi-objective or cross-modality alignment for large models.

In the previous few years, I have worked on Reinforcement Learning, Representations and Robustness.

I'm currently on the full-time job market.

Email / Google Scholar / Github / Twitter

I am a PhD student at UMD CS. I was fortunate to work with Jianwei Yang and Huazhe Xu.

I conducted research at NVIDIA, Adobe, and Microsoft Research. I received my B.S. degree in Mathematics from Sun Yat-sen University.

If you’re interested in my research, potential collaborations, or simply want to catch up, feel free to drop me an email.

May' 26	SAW-Bench won the Best Paper Award Runner-Up at CVPR 2026 WMAS.
Apr' 26	SAW-Bench to appear in ICML 2026 as Spotlight (2%).
Apr' 26	Drop a new blog post about Vibe Agents Step Into the Real World.
Mar' 26	We release a new blog post about Spatial Memory in Frontier Models.
Feb' 26	Three papers to appear in CVPR 2026 (2 main track and 1 findings).
Jan' 26	MomaGraph selected as Oral presentation (1%) in ICLR 2026.
Jan' 26	One papers to appear in ICRA 2026.
Jan' 26	Two papers to appear in ICLR 2026 (ROVER and MomaGraph).
Sept' 25	One paper to appear in NeurIPS 2025.
Feb' 25	Magma to appear in CVPR 2025.
Jan' 25	Two papers to appear in ICLR 2025.
Jan' 25	Start to update Awesome-Generalist-Agents.
Sept' 24	Make-An-Agent to appear in NeurIPS 2024.
June' 24	ACE selected as Oral presentation (1%) in ICML 2024.
May' 24	Two papers to appear in ICML 2024.
Jan' 24	Three papers to appear in ICLR 2024, including two spotlights and one poster.

Selected Publications and Preprints

* denotes Equal Contributions and Project Lead; † indicates Equal Advising.

	Embodied Large Multimodal Model Learning Situated Awareness in the Real World Chuhan Li, Joy Hsu, Yongyuan Liang, Ruilin Han, Rajiv Dhawan, Jiajun Wu, Ming-Hsuan Yang, Xin Eric Wang ICML, 2026 Spotlight, Top 2%* Best Paper Award Runner-Up at CVPR Workshop WMAS, 2026 Project Page / Paper / Benchmark / Twitter
	Embodied Large Multimodal Model MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning Yuanchen Ju, Yongyuan Liang, Yen-Jen Wang, Gireesh Nandiraju, Yuanliang Ju, Seungjae Lee, Qiao Gu, Elvis Hsieh, Furong Huang†, Koushil Sreenath† ICLR, 2026 Oral, Top 1%* Project Page / Paper / Code / Benchmark / Twitter
	Agentic Large Multimodal Model Anticipatory Planning for Multimodal Agents Yongyuan Liang, Shijie Zhou, Yu Gu, Hao Tan, Gang Wu, Franck Dernoncourt, Jihyung Kil, Ryan A. Rossi, Ruiyi Zhang CVPR Findings, 2026 Paper / Twitter
	Unified Multimodal Model WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation Wei Chow, Jiachun Pan, Yongyuan Liang, ..., Weijia Wu, Hanwang Zhang, Tat-Seng Chua, et al. CVPR, 2026 Project Page / Paper / Code / Benchmark / Twitter
	Unified Multimodal Model ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation Yongyuan Liang, Wei Chow, Feng Li, Ziqiao Ma, Xiyao Wang, Jiageng Mao, Jiuhai Chen, Jiatao Gu, Yue Wang†, Furong Huang† ICLR, 2026 Project Page / Paper / Code / Benchmark / Twitter
	3D Large Multimodal Model Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding Yongyuan Liang, Xiyao Wang, Yuanchen Ju, Jianwei Yang, Furong Huang arXiv, 2025 Spotlight Talks at CVPR Workshop CVinW, 2025 Project Page / Paper / Code / Models & Datasets / Twitter
	Agentic Large Multimodal Model Magma: A Foundation Model for Multimodal AI Agents Magma Team CVPR, 2025 Project Page / Paper / Code / Models & Datasets / Twitter
	Embodied Large Multimodal Model TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies Ruijie Zheng, Yongyuan Liang, Shuaiyi Huang, Jianfeng Gao, Hal Daumé III, Andrey Kolobov, Furong Huang, Jianwei Yang ICLR, 2025 Oral Talks at ICLR Workshop GenBot, 2025 Project Page / Paper / Code / Models / Twitter
	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† ICLR**, 2025 Project Page / Paper / Code / Models / Twitter
	Embodied Large Multimodal Model TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos Seungjae Lee, Yoonkyo Jung, Inkook Chun, ..., Yongyuan Liang, Jia-Bin Huang, Furong Huang CVPR*, 2026 Project Page / Paper / Code / Twitter
	Reinforcement Learning Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning Huanyu Li, Kun Lei, Sheng Zang, Kaizhe Hu, Yongyuan Liang, Bo An, Xiaoli Li, Huazhe Xu ICRA, 2026 Project Page / Paper / Code / Twitter
	ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs Xiyao Wang, Zhengyuan Yang, Chao Feng, Yongyuan Liang, Yuhang Zhou, Xiaoyu Liu, Ziyi Zang, Ming Li, Chung-Ching Lin, Kevin Lin, Linjie Li†, Furong Huang†, Lijuan Wang† NeurIPS*, 2025 Project Page / Paper / Code / Models & Datasets / Twitter
	Generative Model 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 Oral Talks at NeurIPS Workshop AFM, 2024 Project Page / Paper / Code / Models & Dataset / Twitter
	Reinforcement Learning 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% Project Page / Paper / Code / 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 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%* Project Page / Paper / Code / Twitter
	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% Project Page / Paper / Code / Twitter
	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 Paper / Twitter
	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
	Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Furong Huang NeurIPS, 2022 Spotlight Talks at NeurIPS Workshop SafeRL, 2021 Paper / Code / Slides
	Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL Yanchao Sun, Ruijie Zheng, Yongyuan Liang, Furong Huang ICLR, 2022 Best Paper Award at NeurIPS Workshop SafeRL, 2021 Project Page / Paper / Code

Blogs

Mar 2026

What We Talk About When We Talk About Spatial Memory in Frontier Models

Spatial Awareness, World Modeling

Apr 2026

Vibes Meet Gravity: AI Agents Step Into the Real World

Vibe Agents, Agentic Multimodal Models

Coming soon

Avocado: Multi-Objective Alignment of Language Models

Alignment Steering, interpretability

Professional Service

Conference Program Committee: ICML(2022-2025), NeurIPS(2021-2025), ICLR(2021-2026)

Workshop Program Committee: FMDM at NeurIPS 2023, Bi-Align at ICLR 2025, CVinW at CVPR 2025

Misc

If my name is a bit tricky to pronounce for you, I’d love to go by Cheryl [ˈʃerəl].

Classic INTJ-A.

I've been playing the violin🎻 for over 15 years and served as Principal First Violin in the university orchestra. I also play the piano for more than 10 years.

I enjoy reading Japanese and Western literature. Here's some of my reading notes.

Been a fan of Novak Djokovic since 2012.

My Erdős number = 4.

life in photos 🍊