Yuancheng Xu
PhD Student in Applied Mathematics
Unversity of Maryland, College Park
Unversity of Maryland, College Park
Email: ycxu [at] umd [dot] edu
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.
![[GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment]](Research/GenARM/main.png)
![[Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models]](Research/Shadowcast/main.png)
![[Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models]](Research/PHTest/main.png)
![[Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making]](Research/ELBERT/main.png)
![[Benchmarking the Robustness of Image Watermarks]](Research/Waves/main.png)
![[Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences]](Research/Mementos/main.png)
![[SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation]](Research/Saflex/main.png)
![[C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder]](Research/C_Disentanglement/main.png)
![[Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness]](Research/DyART/main.png)