Hi! My name is Haoran Sun (ๅญ™็š“็„ถ). I am a second-year PhD student at the Center on Frontiers of Computing Studies, School of Computer Science, Peking University, advised by Prof. Xiaotie Deng. I received my B.E. in Artificial Intelligence (Tong Class) and B.A. in Economics (Double Major) from Yuanpei College, Peking University in 2024.

My broader research interests lie at the intersection of game theory and AI โ€” see our survey [P1]. A line of my work has investigated how to leverage modern AI technology (neural networks) to discover high-revenue auction mechanisms (see [C2], [C7], and [C9]). More recently, I have been focusing on the training of foundation models, specifically post-training mechanisms and infrastructure (see [P6], [C8], [C10], and [P3]). Moreover, I am also interested in the product form of foundation models, i.e., how to monetize in the LLM era (see [P5] and [C6]).

You can find my publications on Google Scholar. Reach me at sunhaoran0301@stu.pku.edu.cn.

๐Ÿ”ฅ News

  • 2026.07: ย ๐ŸŽ‰ Our paper has been accepted to COLM 2026!
  • 2026.05: ย ๐ŸŽ‰ Honored to be awarded the President Scholarship for PhD Students (2026โ€“2027) at Peking University!
  • 2026.05: ย ๐ŸŽ‰ Our paper has been accepted to ICML 2026!
  • 2026.04: ย ๐ŸŽ‰๐ŸŽ‰ Honored to co-organize the AIMS Workshop (AI for Mechanism Design and Strategic Decision Making) at ICLR 2026! Looking forward to seeing you in Rio de Janeiro!

๐Ÿ“ Selected Papers (* indicates equal contribution)

Preprint
sym

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

Haoran Sun*, Wentao Zhang*, Junyang Hua, Hedan Yang, Yongjian Guo, Yifei Zhang, Xiaolong Xiang, Mingxi Luo, Jing Long, Chen Zhao, Chen Zhou, Wanting Xu, Qiming Yang, Hui Zhang, Song Wang, Xiaodong Bai, Shuai Di, Xu Chu, Xiaotie Deng, Yicheng Gong, Junwu Xiong

  • JoyNexus explores a new serviceโ€‘oriented paradigm for multiโ€‘tenant VLA postโ€‘training.
COLM 2026
sym

RL-VLA$^3$: Reinforcement Learning VLA Accelerating via Full Asynchronism

Haoran Sun*, Yongjian Guo*, Zhong Guan*, Shuai Di, Xiaodong Bai, Jing Long, Tianyun Zhao, Mingxi Luo, Hongke Zhao, Likang Wu, Xiaotie Deng, Xu Chu, Xi Xiao, Sheng Wen, Yicheng Gong, Junwu Xiong

  • Efficient asynchronous reinforcement learning framework for Vision-Language-Action models.
ICML 2026
sym

Enhancing Affine Maximizer Auctions with Correlation-Aware Payment

Haoran Sun, Xuanzhi Xia, Xu Chu, Xiaotie Deng

  • Proposed correlation-aware affine maximizer auctions for correlated bidders.
ICLR 2026
sym

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective

Siwei Wang$^*$, Yifei Shen$^*$, Haoran Sun$^*$, Shi Feng$^*$, Shang-Hua Teng, Li Dong, Yaru Hao, Wei Chen

  • Theoretical analysis of RL methods for LLM planning, revealing benefits and pitfalls.
WWW 2026
sym

Scalable Virtual Valuations Combinatorial Auction Design by Combining Zeroth-Order and First-Order Optimization Methods

Zhijian Duan$^*$, Haoran Sun$^*$, Yichong Xia, Siqiang Wang, Zhilin Zhang, Chuan Yu, Jian Xu, Xiaotie Deng

  • Novel combinatorial auction design combining zeroth-order and first-order optimization.
NeurIPS 2025
sym

Mechanism Design for LLM Fine-tuning with Multiple Reward Models

Haoran Sun, Yurong Chen, Siwei Wang, Wei Chen, Xiaotie Deng

  • Mechanism design framework for LLM fine-tuning with multiple reward models.
IJCAI 2025
sym

Game Theory Meets Large Language Models: A Systematic Survey

Haoran Sun, Yusen Wu, Yukun Cheng, Xu Chu

  • Comprehensive survey on the intersection of game theory and LLMs.
NeurIPS 2023 Spotlight
sym

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

Zhijian Duan, Haoran Sun, Yurong Chen, Xiaotie Deng

  • Neural network approach for designing affine maximizer auctions.

See full paper list โ†’


๐ŸŽ– Honors and Awards

  • 2026.05 ๐Ÿ† President Scholarship for PhD Students (2026โ€“2027), Peking University
  • 2024.12 ๐Ÿฅ‰ 3rd Place in NeurIPS 2024 Auto-Bidding in Large-Scale Auctions Competition (General Track)
  • 2024.06 ๐Ÿ† Song Qingling Scholarship, Peking University
  • 2023.10 ๐Ÿ† Yang Fuqing & Wang Yangyuan Academician Scholarship (Top 10%), Peking University
  • 2023.10 ๐Ÿ† Outstanding Research Award, Peking University
  • 2023.08 ๐Ÿฅ‡ 6th Place in IJCAI Mahjong AI Competition (IJCAI 2023); 8th Place (IJCAI 2024)


๐Ÿ’ฌ Academic Service

  • Workshop Organizer: ICLR 2026 Workshop on AI for Mechanism Design and Strategic Decision Making (AIMS)
  • Peer Review: ICLR 2026, NeurIPS (2024-2026), ICML (2024-2026), WWW 2024, COLM 2026, IEEE TCE


๐Ÿ“– Educations

๐Ÿ’ป Internships