Haobo Xu 「徐浩博」

profile.png

Welcome to my homepage!

I am a PhD student at the University of Illinois at Urbana-Champaign, currently advised by Prof. Hanghang Tong. Prior to this, I obtained my bachelor’s degree in Software Engineering from Tsinghua University.

My research interests include Efficient Deep Learning and (Multimodal) Large Language Models.

News

May 14, 2026 Honored to receive the Gold Reviewer Award from ICML 2026!
Apr 6, 2026 Our paper “Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR” was accepted by ACL 2026 as an oral presentation! 🔥🔥
Sep 8, 2025 Graduated from Tsinghua University and started my Ph.D. at UIUC! 🎓
Aug 8, 2025 Our two papers were accepted by CoRL 2025! 🎉
Dec 30, 2024 Grateful to be awarded the National Scholarship! 🎓

Education

Experience

  • Research Scientist Intern @ Meta

    May 2026 – Present
    Menlo Park, CA, USA

Publications

  1. arrol.png
    Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
    Haobo Xu, Sirui Chen, Ruizhong Qiu, and 5 more authors
    ACL (Oral Presentation), 2026
  2. survey.png
    Efficient Diffusion Language Models: A Comprehensive Survey
    Haokun Lin, Xinle Jia, Shaozhen Liu, and 8 more authors
    Preprint, 2026
  3. tavla.png
    TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
    Zongzheng Zhang*, Haobo Xu*, Zhuo Yang*, and 5 more authors
    CoRL, 2025
  4. robochemist.png
    RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation
    Zongzheng Zhang*, Chenghao Yue*, Haobo Xu*, and 5 more authors
    CoRL, 2025
  5. qdlm.png
    Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
    Haokun Lin*, Haobo Xu*, Yichen Wu, and 6 more authors
    Machine Intelligence Research, 2025
  6. duquant.png
    DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
    Haokun Lin*, Haobo Xu*, Yichen Wu*, and 6 more authors
    NeurIPS (Oral Presentation, Acceptance Rate ~0.4%), 2024
  7. slog.png
    SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
    Haobo Xu*, Yuchen Yan*, Dingsu Wang, and 5 more authors
    ICML, 2024

Awards & Honors

  • ICML Gold Reviewer Award, 2026
  • Excellent Graduate, Tsinghua University (清华大学优良毕业生), 2025
  • NeurIPS Top Reviewer Award, 2024
  • China National Scholarship (国家奖学金), 2024
  • NeurIPS Scholar Award, 2024
  • ICML Travel Award, 2024
  • Comprehensive Excellence Award, Tsinghua University, 2021–2024
  • First Provincial-level in Chinese Physics Olympiad, 2018, 2019
  • First Prize in National Olympiad in Informatics in Provinces (NOIP) of China, 2017, 2018

Services

  • Invited Reviewers:
    • 2023: IEEE BigData 2023.
    • 2024: AAAI 2024, NeurIPS 2024.
    • 2025: AAAI 2025, AISTATS 2025, ICLR 2025, ICML 2025, NeurIPS 2025.
    • 2026: AAAI 2026, AISTATS 2026, ICLR 2026, ICML 2026, NeurIPS 2026.

Site Analytics

Visitor map and page-view statistics.

Open Detailed Analytics
Visitor map