About me

I am a research scientist at NVIDIA Research. I just obtained my Ph.D. in 2024 from the Electrical and Computer Engineering department at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Han Zhao and Prof. Bo Li. Previously, I obtained my B.S. in 2019 from UIUC with double majors in (1) Physics, (2) Statistics & Computer Science.

In the past, I have worked on multi-task learning, out-of-distribution (OOD) generalization, domain adaptation and meta-learning. Besides, I have adapted transformers to solve quantum computing problems in Amazon (Paper).

Lately, I have been focusing on large language models and multi-modal models, improving their reliability, efficiency, and controllability. Please check out the following paper list for details.

[Curriculum Vitae]

Selected Recent Publications

[EMNLP 2024] Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang

[TMLR] RLHF Workflow: From Reward Modeling to Online RLHF

Hanze Dong, Wei Xiong, Bo Pang*, Haoxiang Wang*, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang

[ACL 2024] 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

[CVPRW 2024] 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

News

  • [Sep 2024] ArmoRM and Semi-Supervised Reward Modeling (SSRM) are accepted by EMNLP 2024!
  • [Sep 2024] RLHF Workflow is accepeted by TMLR!
  • [May 2024] Have a paper accepted by JMLR! [arXiv]
  • [May 2024] My first LLM alignment paper, Directional Preference Alignment (DPA), is accepted as a long paper in ACL’2024 Main Conference!
  • [Apr 2024] Have a paper accepted by TMLR! [Paper]
  • [Apr 2024] I will join NVIDIA Research as a research scientist in June 2024!
  • [Oct 2023] My Apple internship paper is out! [arXiv] We proposed a simple & efficient method to merge vision foundation models, by which we merged SAM & CLIP into a unified model, SAM-CLIP!
  • [Jan 2023] Will work at Apple AI/ML as a research intern in summer 2023!
  • [Nov 2022] My first quantum computing paper is public! [arXiv, Code]
  • [Oct 2022] Honored to be selected as a top reviewer (8%) of NeurIPS 2022!
  • [Jun 2022] Received a gift award from Unitary Fund for a quantum software project!
  • [May 2022] Have two papers accepted by ICML 2022 and one paper accepted by UAI 2022! [Publications]
  • [Apr 2022] Honored to be selected as one of the Mavis Future Faculty Fellows (MF3) for the 2022-2023 academic year!
  • [Mar 2022] Have one paper accepted by CVPR 2022! [arXiv, code]
  • [Feb 2022] Will work at Amazon Braket (a quantum computing team) as an applied scientist intern in summer 2022!
  • [May 2021] Have one paper accepted by ICML 2021! [arXiv, code]
  • [Jan 2021] Will work at Waymo (formerly the Google self-driving car project) as a research intern in summer 2021!
  • [Oct 2020] Glad to be a reviewer for AAAI 2021, AISTATS 2021 and CVPR 2021!