Yuancheng Xu

PhD Student in Applied Mathematics
Unversity of Maryland, College Park
Email: ycxu [at] umd [dot] edu
About me

My name is Yuancheng Xu (徐源诚) and I am a final-year PhD candidate at the University of Maryland, College Park, where I work with Furong Huang. My research focuses on large language model alignment, AI safety and fairness, as well as enhancing the reasoning and planning capabilities of AI systems. Additionally, I work on controllable video generation, aiming to recreate the world through representations of multimodal content and user-model interactions.

I am currently a research intern at Netflix Eyeline Studios working on video generation.

Research
[GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment]
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
Yuancheng Xu, Udari Madhushani Sehwag, Alec Koppel, Sicheng Zhu, Bang An, Furong Huang, Sumitra Ganesh
International Conference on Learning Representations (ICLR), 2025
  • Propose the Autoregressive Reward Model to efficiently guide next-token generation.
[Paper] [Code] [Project Page]

[Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise]
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
Ryan D Burgert, Yuancheng Xu, Wenqi Xian, Oliver Pilarski, Pascal Clausen, Mingming He, Li Ma, Yitong Deng, Lingxiao Li, Mohsen Mousavi, Michael S Ryoo, Paul Debevec, Ning Yu
Preprint, 2025
[Paper] [Code] [Project Page]

[Scaling Inference-time Search with Vision Value Model for Improved Visual Comprehension]
Scaling Inference-time Search with Vision Value Model for Improved Visual Comprehension
Xiyao Wang, Zhengyuan Yang, Linjie Li, Hongjin Lu, Yuancheng Xu, Chung-Ching Lin, Kevin Lin, Furong Huang, Lijuan Wang
Preprint, 2025
[Paper] [Code]

[Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?]
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
AAAI Conference on Artificial Intelligence (AAAI), 2025
New Frontiers in Adversarial Machine Learning Workshop at Neurips (Best Paper), 2024
[Paper]

[Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models]
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Yuancheng Xu, Jiarui Yao, Manli Shu, Yanchao Sun, Zichu Wu, Ning Yu, Tom Goldstein, Furong Huang
Neural Information Processing Systems (Neurips), 2024
  • First stealthy data poisoning attack against vision-language models.
[Paper] [Code] [Project Page] [Poster]

[Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models]
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
Bang An, Sicheng Zhu, Ruiyi Zhang, Michael-Andrei Panaitescu-Liess, Yuancheng Xu, Furong Huang
Conference on Language Modeling (COLM), 2024
[Paper] [Code] [Project Page]

[Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making]
Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
Yuancheng Xu, Chenghao Deng, Yanchao Sun, Ruijie Zheng, Xiyao Wang, Jieyu Zhao, Furong Huang
International Conference on Machine Learning (ICML), 2024
[Paper] [Code]

[Benchmarking the Robustness of Image Watermarks]
Benchmarking the Robustness of Image Watermarks
Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang
International Conference on Machine Learning (ICML), 2024
[Paper] [Code] [Project Page]

[Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences]
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Gedas Bertasius, Mohit Bansal, Huaxiu Yao, Furong Huang
Association for Computational Linguistics (ACL), 2024
[Paper] [Code] [Project Page]

[SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation]
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Mucong Ding, Bang An, Yuancheng Xu, Anirudh Satheesh, Furong Huang
International Conference on Learning Representations (ICLR), 2024
[Paper]

[C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder]
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, Furong Huang
Neural Information Processing Systems (Neurips), 2023
[Paper] [Code]

[Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness]
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein, Furong Huang
International Conference on Learning Representations (ICLR), 2023
  • Mathematical characterization of how decison boundary moves.
  • Analytic expression for the margin's gradient. Directly applicable to robust training.
[Paper] [Code]