Papers

@article{yang2026bcr2,
  title={Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?},
  author={Yang, Bangji and Ma, Hongbo and Guo, Ruihan and Fan, Jiajun and Zhu, Xi and Liu, Ge},
  journal={arXiv preprint arXiv:2610.22887},
  year={2026},
  url={https://arxiv.org/abs/2610.22887}
}

@article{yang2026tfopd,
  title={Training-Free On-Policy Distillation},
  author={Yang, Bangji and Fan, Jiajun and Zhu, Zhaoyu and Ma, Hongbo and Liu, Ge},
  journal={arXiv preprint arXiv:2610.22236},
  year={2026},
  url={https://arxiv.org/abs/2610.22236}
}

@article{pan2026cleanrm,
  title={CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF},
  author={Pan, Licheng and Yang, Haocheng and Chen, Yuzhou and Sun, Yichen and Lu, Yuan and Teng, Yunfei and Fan, Jiajun and Liu, Guangyi and Chu, Zhixuan and Wang, Hao},
  journal={arXiv preprint arXiv:2610.21138},
  year={2026},
  url={https://arxiv.org/abs/2610.21138}
}

@article{yang2026icw,
  title={Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation},
  author={Yang, Haocheng and Pan, Licheng and Dong, Yiming and Li, Xiaoxi and Lu, Yuan and Chen, Zhenhao and Fan, Jiajun and Shao, Shuai and Zheng, Chunyuan and Wang, Hao},
  journal={arXiv preprint arXiv:2610.19915},
  year={2026},
  url={https://arxiv.org/abs/2610.19915}
}

@article{yang2026rubricarmor,
  title={RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation},
  author={Yang, Haocheng and Zhang, Yuchao and Pan, Licheng and Fan, Jiajun and Wang, Maolin and Zhang, Kangning and Shao, Shuai and Wang, Shijian and Lu, Yuan and Zheng, Chunyuan and Wang, Hao},
  journal={arXiv preprint arXiv:2610.05308},
  year={2026},
  url={https://arxiv.org/abs/2610.05308}
}

@article{yang2026surge,
  title={Does Scaling Reinforcement Learning Really Require More Training?},
  author={Yang, Bangji and Fan, Jiajun and Ma, Hongbo and Guo, Ruihan and Liu, Ge},
  journal={arXiv preprint arXiv:2610.01133},
  year={2026},
  url={https://arxiv.org/abs/2610.01133}
}

@article{yang2026selfpot,
  title={How Much Can Language Models Gain from Test-Time Computation?},
  author={Yang, Bangji and Li, Jingyuan and Fan, Jiajun and Zhang, Yi Evie and Guo, Ruihan and Ma, Hongbo and He, Neil and Liang, Chumeng and Zheng, Qinglong and Ni, Zhanghan and Liu, Ge},
  journal={arXiv preprint arXiv:2610.01110},
  year={2026},
  url={https://arxiv.org/abs/2610.01110}
}

@article{ma2026s3,
  title={$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient},
  author={Ma, Hongbo and Cao, Sansheng and Fan, Jiajun and Yang, Bangji and Liu, Ge},
  journal={arXiv preprint arXiv:2609.37976},
  year={2026},
  url={https://arxiv.org/abs/2609.37976}
}

@article{fan2026speechgym,
  title   = {SpeechGym: An Audio-Native Gym for Training Voice Agents
  via Reinforcement Learning},
  author  = {Jiajun Fan and Jingyuan Li and Prashanth Gurunath Shivakumar
  and Jia-Hong Huang and Qi Luo and M. Maruf and Ivan Bulyko
  and Ge Liu and Roger Ren},
  journal = {arXiv preprint arXiv:2608.26432},
  year    = {2026}
}

@article{fan2026readmind,
  title   = {Can We Read the Mind of an Audio {LLM}? A Verbalizable,
  Multilingual Middle-Layer Workspace},
  author  = {Jiajun Fan and Jingyuan Li and Prashanth Gurunath Shivakumar
  and Qi Luo and Jia-Hong Huang and M. Maruf and Roger Ren
  and Yile Gu and Rahul Pandey and Ge Liu and Ivan Bulyko},
  journal = {arXiv preprint arXiv:2608.24958},
  year    = {2026}
}

@article{cheng2026gpflow,
  title={Variable-Length Generative Protein Design via Generalized Poisson Flow},
  author={Cheng, Chaoran and Ni, Zhanghan and Qu, Yanru and Chen, Yuxin and Guo, Ruihan and Fan, Jiajun and Liu, Ge},
  journal={arXiv preprint arXiv:2607.09039},
  year={2026},
  url={https://arxiv.org/abs/2607.09039}
}

@inproceedings{zheng2026procedure,
  title     = {Procedure-Aware Reinforcement Learning for Tool-Augmented
  Large Language Models},
  author    = {Qinglong Zheng and Jiajun Fan and Chaoran Cheng and Ge Liu},
  booktitle = {Conference on Language Modeling (COLM)},
  year      = {2026},
  url       = {https://openreview.net/forum?id=d4wrBuJ4xo}
}

@article{wang2026proteinzero,
  title   = {ProteinZero: Self-Improving Protein Generation via Online
  Reinforcement Learning},
  author  = {Ziwen Wang and Jiajun Fan and Ruihan Guo and Thao Nguyen
  and Heng Ji and Ge Liu},
  journal = {Transactions on Machine Learning Research},
  year    = {2026},
  url     = {https://arxiv.org/abs/2506.07459}
}

@article{li2026elegantvla,
  title={ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models},
  author={Li, Ye and Liu, Huanan and Ji, Kangye and Meng, Yuan and Fan, Jiajun and Wang, Yuansong and Qin, Shiyu and Wu, Chenglei and Xia, Shu-Tao and Wang, Zhi},
  journal={arXiv preprint arXiv:2605.29438},
  year={2026},
  url={https://arxiv.org/abs/2605.29438}
}

@article{sun2026pyrag,
  title={Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation},
  author={Sun, Jiashuo and Shi, Jimeng and Xie, Yixuan and Wang, Saizhuo and Parekh, Jash Rajesh and Jiang, Pengcheng and Shi, Zhiyi and Fan, Jiajun and Zheng, Qinglong and Li, Peiran and Wang, Shaowen and Liu, Ge and Han, Jiawei},
  journal={arXiv preprint arXiv:2605.12975},
  year={2026},
  url={https://arxiv.org/abs/2605.12975}
}

@inproceedings{yang2026bcr,
  title={Batched Contextual Reinforcement},
  author={Yang, Bangji and Ma, Hongbo and Fan, Jiajun and Liu, Ge},
  booktitle={International Conference on Machine Learning},
  year={2026},
  url={https://openreview.net/forum?id=8Oc3Mx754M}
}

@inproceedings{sun2026barrag,
  title={Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation},
  author={Sun, Jiashuo and Jiang, Pengcheng and Wang, Saizhuo and Fan, Jiajun and Wang, Heng and Ouyang, Siru and Zhong, Ming and Jiao, Yizhu and Huang, Chengsong and Xu, Xueqiang and Han, Pengrui and Li, Peiran and Huang, Jiaxin and Liu, Ge and Ji, Heng and Han, Jiawei},
  booktitle={International Conference on Machine Learning},
  year={2026},
  url={https://openreview.net/forum?id=Tt8lCe1NrW}
}

@article{yang2026m3,
  title={M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning},
  author={Yang, Bangji and Guo, Ruihan and Fan, Jiajun and Cheng, Chaoran and Liu, Ge},
  journal={arXiv preprint arXiv:2602.06166},
  year={2026},
  url={https://arxiv.org/abs/2602.06166}
}

@inproceedings{li2026spvla,
  title={{SP-VLA}: A Joint Model Scheduling and Token Pruning Approach for {VLA} Model Acceleration},
  author={Li, Ye and Meng, Yuan and Sun, Zewen and Ji, Kangye and Tang, Chen and Fan, Jiajun and Ma, Xinzhu and Xia, Shu-Tao and Wang, Zhi and Zhu, Wenwu},
  booktitle={International Conference on Learning Representations},
  year={2026},
  url={https://openreview.net/forum?id=RwdGIIjPlC}
}

@article{li2026prance,
  title={{PRANCE}: Joint Token-Optimization and Structural Channel-Pruning for Adaptive {ViT} Inference},
  author={Li, Ye and Tang, Chen and Meng, Yuan and Fan, Jiajun and Chai, Zenghao and Ma, Xinzhu and Wang, Zhi and Zhu, Wenwu},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2026},
  url={https://arxiv.org/abs/2407.05010}
}

@inproceedings{fan2026incentivizing,
  title     = {Incentivizing Consistent, Effective and Scalable Reasoning
  Capability in Audio {LLM}s via Reasoning Process Rewards},
  author    = {Jiajun Fan and Roger Ren and Jingyuan Li and Rahul Pandey and
  Prashanth Gurunath Shivakumar and Ivan Bulyko and Ankur Gandhe
  and Ge Liu and Yile Gu},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year      = {2026},
  url       = {https://openreview.net/forum?id=DUr48hxO2h}
}

@misc{fan2025finetuningflowmatchinggenerative,
  title={Fine-tuning Flow Matching Generative Models with Intermediate Feedback},
  author={Jiajun Fan and Chaoran Cheng and Shuaike Shen and Xiangxin Zhou and Ge Liu},
  year={2025},
  eprint={2510.18072},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2510.18072}
}

@inproceedings{wang2025varcon,
  title={Variational Supervised Contrastive Learning},
  author={Wang, Ziwen and Fan, Jiajun and Nguyen, Thao and Ji, Heng and Liu, Ge},
  booktitle={Advances in Neural Information Processing Systems},
  year={2025},
  url={https://openreview.net/forum?id=uOOlHOq500}
}

@inproceedings{fan2025adaptive,
  title     = {Adaptive Divergence Regularized Policy Optimization
  for Fine-tuning Generative Models},
  author    = {Jiajun Fan and Tong Wei and Chaoran Cheng and Yuxin Chen and Ge Liu},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems},
  year      = {2025},
  url       = {https://openreview.net/forum?id=aXO0xg0ttW}
}

@article{cheng2025alphaflow,
  title={$\alpha$-Flow: A Unified Framework for Continuous-State Discrete Flow Matching Models},
  author={Cheng, Chaoran and Li, Jiahan and Fan, Jiajun and Liu, Ge},
  journal={arXiv preprint arXiv:2504.10283},
  year={2025},
  url={https://arxiv.org/abs/2504.10283}
}

@inproceedings{fan2025online,
  title={Online Reward-Weighted Fine-Tuning of Flow Matching
  with Wasserstein Regularization},
  author={Jiajun Fan and Shuaike Shen and Chaoran Cheng
  and Yuxin Chen and Chumeng Liang and Ge Liu},
  booktitle={The Thirteenth International Conference on
  Learning Representations},
  year={2025},
  url={https://openreview.net/forum?id=2IoFFexvuw}
}

@inproceedings{fan2024edison,
  title={Efficient Design-and-Control Automation with Reinforcement Learning and Adaptive Exploration},
  author={Fan, Jiajun and Tang, Hongyao and Przystupa, Michael and Phielipp, Mariano and Miret, Santiago and Berseth, Glen},
  booktitle={AI for Accelerated Materials Design (AI4Mat), NeurIPS 2024 Workshop},
  year={2024},
  url={https://openreview.net/forum?id=stiehhc5y6}
}

@article{wang2023convformer,
  title={ConvFormer: Revisiting Transformer for Sequential User Modeling},
  author={Wang, Hao and Lian, Jianxun and Wu, Mingqi and Li, Haoxuan and Fan, Jiajun and Xu, Wanyue and Li, Chaozhuo and Xie, Xing},
  journal={arXiv preprint arXiv:2308.02925},
  year={2023},
  url={https://arxiv.org/abs/2308.02925}
}

@inproceedings{wang2023ot,
  title={Optimal Transport for Treatment Effect Estimation},
  author={Wang, Hao and Fan, Jiajun and Chen, Zhichao and Li, Haoxuan and Liu, Weiming and Liu, Tianqiao and Dai, Quanyu and Wang, Yichao and Dong, Zhenhua and Tang, Ruiming},
  booktitle={Advances in Neural Information Processing Systems},
  year={2023},
  url={https://arxiv.org/abs/2310.18286}
}

@inproceedings{fan2023learnable,
  title={Learnable Behavior Control: Breaking Atari Human World Records
  via Sample-Efficient Behavior Selection},
  author={Jiajun Fan and Yuzheng Zhuang and Yuecheng Liu and Jianye HAO
  and Bin Wang and Jiangcheng Zhu and Hao Wang and Shu-Tao Xia},
  booktitle={The Eleventh International Conference on Learning Representations},
  year={2023},
  url={https://openreview.net/forum?id=FeWvD0L_a4}
}

@InProceedings{pmlr-v162-fan22c,
  title     = {Generalized Data Distribution Iteration},
  author    = {Fan, Jiajun and Xiao, Changnan},
  booktitle = {Proceedings of the 39th International Conference on Machine Learning},
  pages     = {6103--6184},
  year      = {2022},
  editor    = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume    = {162},
  series    = {Proceedings of Machine Learning Research},
  month     = {17--23 Jul},
  publisher = {PMLR},
  pdf       = {https://proceedings.mlr.press/v162/fan22c/fan22c.pdf},
  url       = {https://proceedings.mlr.press/v162/fan22c.html}
}

@article{wang2022escl,
  title={Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications},
  author={Wang, Hao and Chen, Zhichao and Fan, Jiajun and Huang, Yuxin and Liu, Weiming and Liu, Xinggao},
  journal={arXiv preprint arXiv:2210.11039v2},
  year={2022}
}

@inproceedings{xiao2022casaneurips,
  title={CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration},
  author={Xiao, Changnan and Shi, Haosen and Fan, Jiajun and Deng, Shihong and Yin, Haiyan},
  booktitle={Deep Reinforcement Learning Workshop, NeurIPS 2022},
  year={2022}
}

@inproceedings{fan2022gdiworkshop,
  title={GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning},
  author={Fan, Jiajun and Xiao, Changnan and Huang, Yue},
  booktitle={AAAI-22 Workshop on Reinforcement Learning in Games},
  year={2022}
}

@inproceedings{fan2022atarireview,
  title={A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions},
  author={Fan, Jiajun},
  booktitle={AAAI-22 Workshop on Reinforcement Learning in Games},
  year={2022}
}

@article{xiao2021entropy,
  title={An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning},
  author={Xiao, Changnan and Shi, Haosen and Fan, Jiajun and Deng, Shihong},
  journal={arXiv preprint arXiv:2106.00707},
  year={2021}
}

@article{fan2020criticpi2,
  title={Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning},
  author={Fan, Jiajun and Ba, He and Guo, Xian and Hao, Jianye},
  journal={arXiv preprint arXiv:2011.06752},
  year={2020}
}