About me

I am a senior undergraduate student in Computer Science and Technology at Tsinghua University, studying in the Department of Computer Science and Technology and Xinya College. I also minor in Economics and Management at the School of Economics and Management.

My research focuses on building efficient, interpretable, and reliable decision-making systems for cross-modal intelligence. I work with LLMs and VLMs on embodied perception, reasoning, and action under real-world constraints. My broader goal is to develop agents that can understand their environment, reason over context, and act effectively. For more details, see my CV and the publications below.

News

  • 2026.05 — Batched Contextual Reinforcement was accepted by ICML 2026.
  • 2025.11 — StyleTailor was accepted by AAAI 2026 as an Oral presentation (Top 4.5%).
  • 2025.05 — One paper was accepted by ICML 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.
  • 2025.01 — One paper was accepted by ICLR 2025.

Education

2023.09 - Present | Minor in Economics and Management, Tsinghua University

2022.09 - Present | B.S. in Computer Science and Technology, Tsinghua University

Publications

* denotes equal contribution.

Major Author

  1. Cover for Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving

    Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving

    Hongbo Ma*, Bangji Yang*, Yunqian Selina Cheng*, Jiajun Fan, Hanwen Zhang, Ge Liu

    Under Review

  2. Cover for Does RLVR Need Long Rollout Windows? Efficient Training with Concurrent Rewards

    Does RLVR Need Long Rollout Windows? Efficient Training with Concurrent Rewards

    Bangji Yang*, Hongbo Ma*, Ruihan Liu, Jiajun Fan, Xi Zhu, Ge Liu

    Under Review

  3. Cover for S3: Spectral Null-Space Swap Makes Reasoning Models Efficient

    S3: Spectral Null-Space Swap Makes Reasoning Models Efficient

    Hongbo Ma*, Sansheng Cao*, Jiajun Fan, Bangji Yang, Ge Liu

    Under Review

  4. Cover for ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation

    ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation

    Bangji Yang*, Jiajun Fan*, Hongbo Ma*, Xi Zhu, Weizhi Zhang, Minghao Guo, Ye Li, Hamid Palangi, Jiaxuan You

    Under Review

  5. Cover for Does Scaling Reinforcement Learning Really Require More Training?

    Does Scaling Reinforcement Learning Really Require More Training?

    Bangji Yang*, Jiajun Fan*, Hongbo Ma*, Ruihan Guo*, Ge Liu

    Under Review

  6. Cover for Auditing Generated Skill Libraries for Embodied Language Agents

    Section-Aware Auditting and Compression of Generated Skill Libraries for Language Agents

    Bangji Yang*, Hongbo Ma*, Qinglong Zheng*, Jiajun Fan, JIA-HONG HUANG, Ge Liu

    Under Review

  7. Cover for Batched Contextual Reinforcement

    Batched Contextual Reinforcement

    Bangji Yang*, Hongbo Ma*, Jiajun Fan, Ge Liu

    ICML 2026 Poster

    Paper

Secondary Author

  1. Cover for Training-Free On-Policy Distillation

    Training-Free On-Policy Distillation

    Bangji Yang*, Jiajun Fan*, Zhaoyu Zhu, Hongbo Ma, Ge Liu

    Under Review

  2. Cover for How Much Can Language Models Gain from Test-Time Computation?

    How Much Can Language Models Gain from Test-Time Computation?

    Bangji Yang, Jingyuan Li, Jiajun Fan, Yi Evie Zhang, Ruihan Guo, Hongbo Ma, Neil He, Chumeng Liang, Qinglong Zheng, Zhanghan Ni, Ge Liu

    Under Review

  3. Cover for Towards Generalist Game Players: A Survey of Foundation Models in the Game Multiverse

    Towards Generalist Game Players: A Survey of Foundation Models in the Game Multiverse

    Kuan Zhang*, Dongchen Liu*, Qiyue Zhao*, Tianyu Xin*, Yue Su*, Haisheng Wang, Han Yin, Hongbo Ma, Peize Li, Tianjun Gu, Xiangnan Wu, Xinran Zhang, Yongxuan Li, Zirong Chen, Yiming Li

    Under Review

    Paper

Research Experience

2025.12 - Present | Research Intern Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign

2025.09 - 2025.10 | Research Intern i-Vision Group, Tsinghua University

2025.05 - 2025.08 | Research Intern Guangming Lab, Shenzhen

2024.07 - 2025.02 | Research Intern GenSi Lab, Tsinghua University

2024.02 - 2024.06 | Research Intern ATOM Lab, Tsinghua University

Academic Service

  • NeurIPS 2026, Reviewer
  • ICML 2026 Workshop AI4Math, Reviewer
  • ACL ARR 2026 May, 2026 Oct, Reviewer
  • AAAI 2027, Program Committee
  • ICLR 2027, Reviewer

Invited Talks

Awards & Scholarships

  • 2025 - 2026 | Comprehensive Excellence Scholarship, Tsinghua University
  • 2024 - 2025 | Outstanding Scientific and Technological Innovation Scholarship, Tsinghua University
  • 2024 - 2025 | Outstanding Social Work Scholarship, Tsinghua University
  • 2023 - 2024 | Outstanding Student Leader, Tsinghua University
  • 2023 - 2024 | Outstanding Social Work Scholarship, Tsinghua University
  • 2022 - 2023 | Outstanding Social Work Scholarship, Tsinghua University
  • 2022 - 2026 | Second Prize Freshman Scholarship, Tsinghua University

Misc

I love writing. For longer reflections, visit my Zhihu. I also share shorter updates on Rednote and collect posts on my blog page.