About

Hi, I am Haikang Deng, a second-year PhD at UCLA under the supervision of Prof. Nanyun Peng. My research interests lie in the intersection of natural language processing and machine learning, with a focus on controlled generation and diversity methods. I did my undergrad at UNC Chapel Hill where I was advised by Prof. Colin Raffel.

Research

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier
Eric Jiang, Xiao Liang, Yikai Zhang, Yingjia Wan, Mengting Li, Haikang Deng, Alexander K. Taylor, Justin Baker, Rushil Raghavan, Junyi Zhang, Ying Nian Wu, Andrea L. Bertozzi, Kai-Wei Chang, Raghu Meka, Matthew Sottile, Nanyun Peng, Amit Sahai, Terence Tao, Wei Wang arXiv Preprint, 2026
arXiv · PDF

Decoupling Task-Solving and Output Formatting in LLM Generation
Haikang Deng, Po-Nien Kung, Nanyun Peng ACL, 2026 Oral
arXiv · PDF · Code · Video

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?
Alexander K. Taylor, Junyi Zhang, Ethan Ji, Vigyan Sahai, Haikang Deng, Yuanzhou Chen, Yifan Yuan, Di Wu, Jia-Chen Gu, Kai-Wei Chang, Nanyun Peng, Amit Sahai, Wei Wang arXiv Preprint, 2026
arXiv · PDF · Code

Learning Structured Reasoning via Tractable Trajectory Control
Po-Nien Kung, Zhen Yang, Jeffrey Luo, Cheng-Fu Yang, Haikang Deng, Zi-Yi Dou, Yinfei Yang, Nanyun Peng, Zhe Gan, Kai-Wei Chang ICML, 2026 Spotlight
arXiv · PDF

DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation
Yu Zhou, Sohyun An, Haikang Deng, Da Yin, Clark Peng, Cho-Jui Hsieh, Kai-Wei Chang, Nanyun Peng arXiv Preprint, 2025
arXiv · PDF · Code

Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Haikang Deng, Colin Raffel EMNLP, 2023
arXiv · PDF · Code

Large Language Models Struggle to Learn Long Tail Knowledge
Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, Colin Raffel ICML, 2023
arXiv · PDF · Code