Publications

(* indicates equal contribution)

• Efficiently Editing Mixture-of-Experts Models with Compressed Experts.[code]
  Yifei He, Yang Liu, Chen Liang, Hany Awadalla.
• Scaling Laws for Multilingual Language Models.
  Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, Xia Song.
  
• Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach.
  Siqi Zeng, Yifei He, Weiqiu You, Yifan Hao, Yao-Hung Hubert Tsai, Makoto Yamada, Han Zhao.
• Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks.
  Samuele Poppi, Zheng-Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi.
  NAACL 2025 Findings.
• Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic.[code]
  Yifei He, Yuzheng Hu, Yong Lin, Tong Zhang, Han Zhao.
  TMLR.
• Semi-Supervised Reward Modeling via Iterative Self-Training.[code]
  Yifei He*, Haoxiang Wang*, Ziyan Jiang, Alexandros Papangelis, Han Zhao.
  EMNLP 2024 Findings.
• Robust Multi-Task Learning with Excess Risks.[code]
  Yifei He, Shiji Zhou, Guojun Zhang, Hyokun Yun, Yi Xu, Belinda Zeng, Trishul Chilimbi, Han Zhao.
  ICML 2024.
• Gradual Domain Adaptation: Theory and Algorithms.[code]
  Yifei He*, Haoxiang Wang*, Bo Li, Han Zhao.
  JMLR.
• Efficient Modality Selection in Multimodal Learning.
  Yifei He*, Runxiang Cheng*, Gargi Balasubramaniam*, Yao-Hung Hubert Tsai, Han Zhao.
  JMLR.
• Greedy Modality Selection via Approximate Submodular Maximization.
  Runxiang Cheng*, Gargi Balasubramaniam*, Yifei He*, Yao-Hung Hubert Tsai, Han Zhao.
  UAI 2022.
• A Hierarchical Approach to Multi-Event Survival Analysis.
  Donna Tjandra, Yifei He, Jenna Wiens.
  AAAI 2021.
• Conformer-RL: A Deep Reinforcement Learning Library for Conformer Generation.
  Runxuan Jiang, Tarun Gogineni, Joshua Kammeraad, Yifei He, Ambuj Tewari, Paul Zimmerman.
  Journal of Computational Chemistry.