Publications

(* indicates equal contribution)

• Scaling Laws for Multilingual Language Models.
  Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, Xia Song.
  Preprint.

• Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic.[code]
  Yifei He, Yuzheng Hu, Yong Lin, Tong Zhang, Han Zhao.
  Preprint.

• Semi-Supervised Reward Modeling via Iterative Self-Training.[code]
  Yifei He*, Haoxiang Wang*, Ziyan Jiang, Alexandros Papangelis, Han Zhao.
  In Findings of the Association for Computational Linguistics: EMNLP 2024. (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.
  In Proceeding of the 41st International Conference on Machine Learning. (ICML 2024)
• Gradual Domain Adaptation: Theory and Algorithms.[code]
  Yifei He*, Haoxiang Wang*, Bo Li, Han Zhao.
  In Journal of Machine Learning Research. (JMLR 2024)
• Efficient Modality Selection in Multimodal Learning.
  Yifei He*, Runxiang Cheng*, Gargi Balasubramaniam*, Yao-Hung Hubert Tsai, Han Zhao.
  In Journal of Machine Learning Research. (JMLR 2024)
  (Extended version of our UAI 2022 paper “Greedy Modality Selection via Approximate Submodular Maximization.”)
• Greedy Modality Selection via Approximate Submodular Maximization.
  Runxiang Cheng*, Gargi Balasubramaniam*, Yifei He*, Yao-Hung Hubert Tsai, Han Zhao.
  In Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence. (UAI 2022)
• A Hierarchical Approach to Multi-Event Survival Analysis.
  Donna Tjandra, Yifei He, Jenna Wiens.
  In Proceedings of the 35th AAAI Conference on Artificial Intelligence. (AAAI 2021)
• Conformer-RL: A Deep Reinforcement Learning Library for Conformer Generation.
  Runxuan Jiang, Tarun Gogineni, Joshua Kammeraad, Yifei He, Ambuj Tewari, Paul Zimmerman.
  In Journal of Computational Chemistry.