Publications

Publications

( * indicates equal contribution. )

1. Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards Haoxiang Wang*, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

2. SAM-CLIP: Merging Vision Foundation Models Towards Semantic and Spatial Understanding
   Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari

3. Enhancing Compositional Generalization via Compositional Feature Alignment

   Haoxiang Wang*, Haozhe Si*, Huajie Shao, Han Zhao

   Transactions on Machine Learning Research (TMLR), 2024

4. Gradual Domain Adaptation: Theory and Algorithms

   Yifei He, Haoxiang Wang, Bo Li, Han Zhao

   Submitted to Journal of Machine Learning Research (JMLR)

5. Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms

   Haoxiang Wang, Gargi Balasubramaniam, Haozhe Si, Bo Li, Han Zhao

   Submitted to Journal of Machine Learning Research (JMLR)

6. Predicting Properties of Quantum Systems with Conditional Generative Models [Code]

   Haoxiang Wang, Maurice Weber, Josh Izaac, Cedric Yen-Yu Lin

   2022

7. Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond [Code]

   Haoxiang Wang, Bo Li, Han Zhao

   International Conference on Machine Learning (ICML), 2022

8. Provable Domain Generalization via Invariant-Feature Subspace Recovery [Code]

   Haoxiang Wang, Haozhe Si, Bo Li, Han Zhao

   International Conference on Machine Learning (ICML), 2022

9. Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation System

Mao Ye, Ruichen Jiang, <u>Haoxiang Wang</u>, Dhruv Choudhary, Xiaocong Du, Bhargav Bhushanam, Aryan Mokhtari, Arun Kejariwal, Qiang Liu

*Uncertainty in Artificial Intelligence (**UAI**), 2022*

1. Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning [Code]

<u>Haoxiang Wang</u>\*, Yite Wang\*, Ruoyu Sun, Bo Li

*Conference on Computer Vision and Pattern Recognition (**CVPR**), 2022*

1. Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation [Code, Video, Slides]

   Haoxiang Wang, Han Zhao, Bo Li

   International Conference on Machine Learning (ICML), 2021

2. Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets

   Haoxiang Wang, Ruoyu Sun, Bo Li

   arXiv, 2020

3. Learning Positive Functions with Pseudo Mirror Descent

   Yingxiang Yang, Haoxiang Wang, Negar Kiyavash, Niao He.

   Advances in Neural Information Processing Systems (NeurIPS), 2019 (spotlight, acceptance rate: 164/6743 = 2.4%)