Publications

📚 View full profile on Google Scholar

Publications are listed in reverse chronological order. * denotes first authorship.

International Conference on Learning Representations 2026 (ICLR 2026)
SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
Ye Li, Yuan Meng, Zewen Sun, Kangye Ji, Chen Tang, Jiajun Fan, Xinzhu Ma, Shu-Tao Xia, Zhi Wang, Wenwu Zhu. "SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration." ICLR 2026.
International Conference on Learning Representations 2026 (ICLR 2026)
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards 🔗 Project
Jiajun Fan, Roger Ren, Jingyuan Li, Rahul Pandey, Prashanth G. Shivakumar, Ankur Gandhe, Ge Liu, Yile Gu, Ivan Bulyko. "Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards." ICLR 2026.
arXiv preprint (Under Review), 2025
Fine-tuning Flow Matching Generative Models with Intermediate Feedback 🔗 Project
Jiajun Fan, Chaoran Cheng, Shuaike Shen, Xiangxin Zhou, Ge Liu. "Fine-tuning Flow Matching Generative Models with Intermediate Feedback." arXiv:2510.18072, 2025.
arXiv preprint (Under Review), 2025
ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning
Ziwen Wang, Jiajun Fan, Rui Guo, Thao Nguyen, Heng Ji, Ge Liu. "ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning." arXiv:2506.07459, 2025.
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Variational Supervised Contrastive Learning
Ziwen Wang, Jiajun Fan, Thao Nguyen, Heng Ji, Ge Liu. "Variational Supervised Contrastive Learning." NeurIPS 2025.
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models 🔗 Project
Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen, Ge Liu. "Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models." NeurIPS 2025.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
Ye Li, Chen Tang, Yuan Meng, Jiajun Fan, Zenghao Chai, Xinzhu Ma, Zhi Wang, Wenwu Zhu. "PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference." TPAMI 2026.
International Conference on Learning Representations 2025 (ICLR 2025)
Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization 🔗 Project
Jiajun Fan, Shuaike Shen, Chaoran Cheng, Yuxin Chen, Chumeng Liang, Ge Liu. "Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization." ICLR 2025.
NeurIPS 2024 Workshop on AI for New Drug Modalities (AI4Mat)
Efficient Design-and-Control Automation with Reinforcement Learning and Adaptive Exploration
Jiajun Fan, et al. "Efficient Design-and-Control Automation with Reinforcement Learning and Adaptive Exploration." NeurIPS 2024 Workshop AI4Mat.
Conference on Neural Information Processing Systems 2023 (NeurIPS 2023)
Optimal Transport for Treatment Effect Estimation
Hao Wang, Jiajun Fan, Zhichao Chen, Haoran Li, Weiming Liu, Tianqiao Liu, Quanyu Dai, Yichao Wang, Zhenhua Dong, Ruiming Tang. "Optimal Transport for Treatment Effect Estimation." NeurIPS 2023.
International Conference on Learning Representations 2023 (ICLR 2023, Oral — Notable Top 5%)
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection 🔗 Project
Jiajun Fan, Yuzheng Zhuang, Yuecheng Liu, Jianye Hao, Bin Wang, Jiangcheng Zhu, Hao Wang, Shu-Tao Xia. "Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection." ICLR 2023, oral (ranked 5/4176).
In the proceedings of International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA
Generalized Data Distribution Iteration 🔗 Project
Jiajun Fan, Changnan Xiao, "Generalized Data Distribution Iteration." In the proceedings of International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, 2022.
Arxiv
Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications
Hao Wang, Zhichao Chen, Jiajun Fan, Yuxin Huang, Weiming Liu, Xinggao Liu, "Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications." Arxiv, 2022.
In the proceedings of Deep Reinforcement Learning Workshop NeurIPS 2022
CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin, "CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration." In the proceedings of Deep Reinforcement Learning Workshop NeurIPS 2022, 2022.
In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 🔗 Project
Jiajun Fan, Changnan Xiao, Yue Huang, "GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning." In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games, 2021.
Arxiv
CASA: A Bridge Between Gradient of Policy Improvement and Policy Evaluation
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, "CASA: A Bridge Between Gradient of Policy Improvement and Policy Evaluation." Arxiv, 2021.
Arxiv
An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, "An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning." Arxiv, 2021.
In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games
A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions
Jiajun Fan, "A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions." In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games, 2021.
Arxiv
Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning
Jiajun Fan, He Ba, Xian Guo, Jianye Hao, "Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning." Arxiv, 2020.