Yuancheng Xu

Research Scientist, Netflix

Joined

May 2022

Names

Yuancheng Xu (Preferred)

Emails

****@umd.edu (Confirmed)

****@gmail.com (Confirmed)

****@netflix.com (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Research Scientist

Netflix (netflix.com)

2025 – Present

PhD student

Computer Science, University of Maryland, College Park (umd.edu)

2020 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Furong Huang

2020 – Present

Coauthor

Tom Goldstein

2020 – Present

Expertise

Video Generation

2024 – Present

Large Language Models

2023 – Present

Publications

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
Udari Madhushani Sehwag, Shayan Shabihi, Alex McAvoy, Vikash Sehwag, Yuancheng Xu, Dalton towers, Furong Huang
- ICLR 2026 Poster
- Readers: Everyone
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
Baijiong Lin, Weisen Jiang, Yuancheng Xu, Hao Chen, Ying-Cong Chen
- ICML 2025 poster
- Readers: Everyone
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
- SSI-FM Poster
- Readers: Everyone
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
- Reasoning and Planning for LLMs @ ICLR2025
- Readers: Everyone
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
- ICLR 2025 Workshop World Models
- Readers: Everyone
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
- ICLR 2025 Poster
- Readers: Everyone
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
- AdvML-Frontiers 2024
- Readers: Everyone
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
- NextGenAISafety 2024 Poster
- Readers: Everyone
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
- NextGenAISafety 2024 Poster
- Readers: Everyone
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
- NeurIPS 2024 poster
- Readers: Everyone

View all 23 publications

Co-Authors

View all 48 co-authors