Publications

2026

1. NeurIPS 2026

   From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

   Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng , Xinpeng Ti, Liyao Li, Zhanming Shen, Peng LU, and 2 more authors

   In Advances in Neural Information Processing Systems, 2026

   Bib

   @inproceedings{ye2026structural,
     title = {From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors},
     author = {Ye, Wentao and Ye, Yali and Xiao, Zhiqing and Peng, Ru and Ti, Xinpeng and Li, Liyao and Shen, Zhanming and LU, Peng and Zhang, Jie and Wang, Haobo},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2026},
     dimensions = {true},
   }

2. NeurIPS 2026

   

   From “Weak” Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

   Qi Sun, Siyue Zhang, Yulin Chen, Yuxiang Xue, Ru Peng , and Chen Zhao

   In Advances in Neural Information Processing Systems, 2026

   Bib PDF

   @inproceedings{sun2026weak,
     title = {From ``Weak'' Signals to Strong Models: Preference Delta Aggregation with LoRA Merging},
     author = {Sun, Qi and Zhang, Siyue and Chen, Yulin and Xue, Yuxiang and Peng, Ru and Zhao, Chen},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2026},
     dimensions = {true},
   }

3. EMNLP Findings 2026

   

   MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making

   Zhiting Fan, Ruizhe Chen, Hualiang Wang, Ru Peng , Zijie Meng, Wen Ma, Jian Wu, and Zuozhu Liu

   In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026

   Bib

   @inproceedings{fan2026medace,
     title = {MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making},
     author = {Fan, Zhiting and Chen, Ruizhe and Wang, Hualiang and Peng, Ru and Meng, Zijie and Ma, Wen and Wu, Jian and Liu, Zuozhu},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
     year = {2026},
     dimensions = {true},
   }

4. EMNLP 2026

   

   TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

   Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang, Lizhou Cai, Yixiu Mao, Ru Peng , Xin Xu, and 4 more authors

   In Conference on Empirical Methods in Natural Language Processing, 2026

   Bib PDF

   @inproceedings{zou2026trace,
     title = {TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning},
     author = {Zou, Heming and Wang, Qi and Qu, Yun and Jiang, Yuhang and Cai, Lizhou and Mao, Yixiu and Peng, Ru and Xu, Xin and Liu, Weijie and Yang, Kai and Yang, Saiyong and Ji, Xiangyang},
     booktitle = {Conference on Empirical Methods in Natural Language Processing},
     year = {2026},
     dimensions = {true},
   }

5. Hy4P Tech Report

   

   Hy4-preview model card

   Tencent Hy Team

   Aug 2026

   Bib PDF

   @misc{hy4preview2026,
     title = {Hy4-preview model card},
     author = {Team, Tencent Hy},
     year = {2026},
     month = aug,
   }

6. ArXiv 2026

   

   BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences

   Ru Peng , Haokai Xu, Xijun Gu, Tianyu Zhao, Zhiting Fan, Yawen Zeng, Yihong Zhuang, Jinyang Zhang, and 7 more authors

   arXiv preprint arXiv:2607.27366, Aug 2026

   Bib PDF

   @article{peng2026bridgealign,
     title = {BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences},
     author = {Peng, Ru and Xu, Haokai and Gu, Xijun and Zhao, Tianyu and Fan, Zhiting and Zeng, Yawen and Zhuang, Yihong and Zhang, Jinyang and Yang, Kexin and Wu, Jian and Chen, Hao and Wang, Haobo and Lin, Junyang and Liu, Dayiheng and Zhao, Junbo},
     journal = {arXiv preprint arXiv:2607.27366},
     year = {2026},
     dimensions = {true},
   }

7. ACL Findings 2026

   

   HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs

   Ru Peng , Tianyu Zhao, Xijun Gu, Zhiting Fan, Haokai Xu, Jinyang Zhang, Yawen Zeng, Yihong Zhuang, and 4 more authors

   In Findings of the Association for Computational Linguistics: ACL 2026, Aug 2026

   Bib PDF

   @inproceedings{peng2026hsssynth,
     title = {HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs},
     author = {Peng, Ru and Zhao, Tianyu and Gu, Xijun and Fan, Zhiting and Xu, Haokai and Zhang, Jinyang and Zeng, Yawen and Zhuang, Yihong and Yang, Kexin and Lin, Junyang and Liu, Dayiheng and Zhao, Junbo},
     booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
     year = {2026},
     dimensions = {true},
   }

8. Hy3 Tech Report

   

   Hy3 model card

   Tencent Hy Team

   Jul 2026

   Bib PDF

   @misc{hy32026,
     title = {Hy3 model card},
     author = {Team, Tencent Hy},
     year = {2026},
     month = jul,
   }

9. ArXiv 2026

   

   Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization

   Hao Chen, Zhanming Shen, Liyao Li, Yanyu Chen, Xuhang Zhu, Xiaomeng Hu, Qi Zhang, Ru Peng , and 3 more authors

   arXiv preprint arXiv:2606.08815, Jul 2026

   Bib PDF

   @article{chen2026momentum,
     title = {Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization},
     author = {Chen, Hao and Shen, Zhanming and Li, Liyao and Chen, Yanyu and Zhu, Xuhang and Hu, Xiaomeng and Zhang, Qi and Peng, Ru and Shen, Xiaoyu and Wang, Haobo and Zhao, Junbo},
     journal = {arXiv preprint arXiv:2606.08815},
     year = {2026},
     dimensions = {true},
   }

10. Hy3P Tech Report

    

    Hy3-preview model card

    Tencent Hy Team

    Apr 2026

    Bib PDF

    @misc{hy3preview2026,
      title = {Hy3-preview model card},
      author = {Team, Tencent Hy},
      year = {2026},
      month = apr,
    }

11. ICLR 2026

    

    OptimSyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation

    Zhiting Fan, Ruizhe Chen, Tianxiang Hu, Ru Peng , Zenan Huang, Haokai Xu, Yixin Chen, Jian Wu, and 2 more authors

    In The Fourteenth International Conference on Learning Representations, Apr 2026

    Bib PDF

    @inproceedings{fan2026optimsyn,
      title = {OptimSyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation},
      author = {Fan, Zhiting and Chen, Ruizhe and Hu, Tianxiang and Peng, Ru and Huang, Zenan and Xu, Haokai and Chen, Yixin and Wu, Jian and Zhao, Junbo and Liu, Zuozhu},
      booktitle = {The Fourteenth International Conference on Learning Representations},
      year = {2026},
      url = {https://openreview.net/forum?id=vFcm5sOitq},
      dimensions = {true},
    }

12. SCIS 2026

    

    DataXman: Selecting and Mixing Pretraining Data via Bilingual Mixture-of-Experts Data Manager

    Ru Peng , Jinyang Zhang, Yawen Zeng, Kexin Yang, Junyang Lin, Haobo Wang, Gang Chen, Jingren Zhou, and 2 more authors

    Science China Information Sciences, Apr 2026

    Bib PDF

    @article{peng2026dataxman,
      title = {DataXman: Selecting and Mixing Pretraining Data via Bilingual Mixture-of-Experts Data Manager},
      author = {Peng, Ru and Zhang, Jinyang and Zeng, Yawen and Yang, Kexin and Lin, Junyang and Wang, Haobo and Chen, Gang and Zhou, Jingren and Liu, Dayiheng and Zhao, Junbo},
      journal = {Science China Information Sciences},
      year = {2026},
      dimensions = {true},
    }

13. Machine Learning 2026

    

    W2S: Weak-to-Strong Prompt Correction for Large Language Models

    Lirong Gao, Xinyi Wang, Hao Chen, Ru Peng , Qi Zhang, Yiming Zhang, Wentao Ye, Haoze Li, and 2 more authors

    Machine Learning, Apr 2026

    Bib PDF Code

    @article{gao2026w2s,
      title = {W2S: Weak-to-Strong Prompt Correction for Large Language Models},
      author = {Gao, Lirong and Wang, Xinyi and Chen, Hao and Peng, Ru and Zhang, Qi and Zhang, Yiming and Ye, Wentao and Li, Haoze and Wang, Haobo and Zhao, Junbo},
      journal = {Machine Learning},
      volume = {115},
      number = {3},
      pages = {47},
      year = {2026},
      publisher = {Springer},
      dimensions = {true},
    }

2025

1. Ant RL Tech Report

   

   Reinforcement learning with rubric anchors

   Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng , Jiaqi Hu, and 3 more authors

   arXiv preprint arXiv:2508.12790, Apr 2025

   Bib PDF

   @article{huang2025reinforcement,
     title = {Reinforcement learning with rubric anchors},
     author = {Huang, Zenan and Zhuang, Yihong and Lu, Guoshan and Qin, Zeyu and Xu, Haokai and Zhao, Tianyu and Peng, Ru and Hu, Jiaqi and Shen, Zhanming and Hu, Xiaomeng and others},
     journal = {arXiv preprint arXiv:2508.12790},
     year = {2025},
     dimensions = {true},
   }

2. ACL Findings 2025

   

   Llm-enhanced query generation and retrieval preservation for task-oriented dialogue

   Jiale Chen, Xuelian Dong, Wenxiu Xie, Ru Peng , Kun Zeng, and Tianyong Hao

   In Findings of the Association for Computational Linguistics: ACL 2025, Apr 2025

   Bib PDF

   @inproceedings{chen2025llm,
     title = {Llm-enhanced query generation and retrieval preservation for task-oriented dialogue},
     author = {Chen, Jiale and Dong, Xuelian and Xie, Wenxiu and Peng, Ru and Zeng, Kun and Hao, Tianyong},
     booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
     pages = {14307--14321},
     year = {2025},
     dimensions = {true},
   }

3. ICLR 2025

   

   DataMan: Data Manager for Pre-training Large Language Models

   Ru Peng , Kexin Yang, Yawen Zeng, Junyang Lin, Dayiheng Liu, and Junbo Zhao

   In The Thirteenth International Conference on Learning Representations, Apr 2025

   Bib PDF Code

   @inproceedings{pengdataman,
     title = {DataMan: Data Manager for Pre-training Large Language Models},
     author = {Peng, Ru and Yang, Kexin and Zeng, Yawen and Lin, Junyang and Liu, Dayiheng and Zhao, Junbo},
     booktitle = {The Thirteenth International Conference on Learning Representations},
     year = {2025},
     dimensions = {true},
   }

2024

1. Qwen2.5 Technical Report

   

   Qwen2.5 Technical Report

   An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, and 33 more authors

   arXiv preprint arXiv:2412.15115, Apr 2024

   Bib PDF Code

   @article{qwen2.5,
     title = {Qwen2.5 Technical Report},
     author = {Yang, An and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and Wei, Haoran and Lin, Huan and Yang, Jian and Tu, Jianhong and Zhang, Jianwei and Yang, Jianxin and Yang, Jiaxi and Zhou, Jingren and Lin, Junyang and Dang, Kai and Lu, Keming and Bao, Keqin and Yang, Kexin and Yu, Le and Li, Mei and Xue, Mingfeng and Zhang, Pei and Zhu, Qin and Men, Rui and Lin, Runji and Li, Tianhao and Xia, Tingyu and Ren, Xingzhang and Ren, Xuancheng and Fan, Yang and Su, Yang and Zhang, Yichang and Wan, Yu and Liu, Yuqiong and Cui, Zeyu and Zhang, Zhenru and Qiu, Zihan},
     journal = {arXiv preprint arXiv:2412.15115},
     year = {2024},
     dimensions = {true},
   }

2. EMNLP 2024

   

   Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

   Chenhan Yuan, Fei Huang, Ru Peng , Keming Lu, Bowen Yu, Chang Zhou, and Jingren Zhou

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Apr 2024

   Bib PDF Code

   @inproceedings{yuan2024predicting,
     title = {Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model},
     author = {Yuan, Chenhan and Huang, Fei and Peng, Ru and Lu, Keming and Yu, Bowen and Zhou, Chang and Zhou, Jingren},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
     pages = {5527--5542},
     year = {2024},
     dimensions = {true},
   }

3. EMNLP 2024

   

   Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection

   Xiaomeng Hu, Yiming Zhang, Ru Peng , Haozhe Zhang, Chenwei Wu, Gang Chen, and Junbo Zhao

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Apr 2024

   Bib PDF

   @inproceedings{hu2024embedding,
     title = {Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection},
     author = {Hu, Xiaomeng and Zhang, Yiming and Peng, Ru and Zhang, Haozhe and Wu, Chenwei and Chen, Gang and Zhao, Junbo},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
     pages = {1950--1959},
     year = {2024},
     dimensions = {true},
   }

4. EMNLP Findings 2024

   

   Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

   Qin Zhu, Qinyuan Cheng, Runyu Peng, Xiaonan Li, Ru Peng , Tengxiao Liu, Xipeng Qiu, and Xuan-Jing Huang

   In Findings of the Association for Computational Linguistics: EMNLP 2024, Apr 2024

   Bib PDF Code

   @inproceedings{zhu2024inference,
     title = {Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation},
     author = {Zhu, Qin and Cheng, Qinyuan and Peng, Runyu and Li, Xiaonan and Peng, Ru and Liu, Tengxiao and Qiu, Xipeng and Huang, Xuan-Jing},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
     pages = {9113--9129},
     year = {2024},
     dimensions = {true},
   }

5. ACL Findings 2024

   

   DORY: Deliberative Prompt Recovery for LLM

   Lirong Gao, Ru Peng , Yiming Zhang, and Junbo Zhao

   In Findings of the Association for Computational Linguistics ACL 2024, Apr 2024

   Bib PDF

   @inproceedings{gao2024dory,
     title = {DORY: Deliberative Prompt Recovery for LLM},
     author = {Gao, Lirong and Peng, Ru and Zhang, Yiming and Zhao, Junbo},
     booktitle = {Findings of the Association for Computational Linguistics ACL 2024},
     pages = {10614--10632},
     year = {2024},
     dimensions = {true},
   }

6. Qwen2 Technical Report

   

   Qwen2 technical report, 2024

   An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, and 3 more authors

   arXiv preprint arXiv:2407.10671, Apr 2024

   Bib PDF Code

   @article{yang2407qwen2,
     title = {Qwen2 technical report, 2024},
     author = {Yang, An and Yang, Baosong and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Zhou, Chang and Li, Chengpeng and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and others},
     journal = {arXiv preprint arXiv:2407.10671},
     year = {2024},
     dimensions = {true},
   }

7. ArXiv 2024

   

   Dotamath: Decomposition of thought with code assistance and self-correction for mathematical reasoning

   Chengpeng Li, Guanting Dong, Mingfeng Xue, Ru Peng , Xiang Wang, and Dayiheng Liu

   arXiv preprint arXiv:2407.04078, Apr 2024

   Bib PDF Code

   @article{li2024dotamath,
     title = {Dotamath: Decomposition of thought with code assistance and self-correction for mathematical reasoning},
     author = {Li, Chengpeng and Dong, Guanting and Xue, Mingfeng and Peng, Ru and Wang, Xiang and Liu, Dayiheng},
     journal = {arXiv preprint arXiv:2407.04078},
     year = {2024},
     dimensions = {true},
   }

8. ICLR 2024

   

   Energy-based Automated Model Evaluation

   Ru Peng , Heming Zou, Haobo Wang, Yawen Zeng, Zenan Huang, and Junbo Zhao

   In The Twelfth International Conference on Learning Representations, Apr 2024

   Bib PDF Code

   @inproceedings{pengenergy,
     title = {Energy-based Automated Model Evaluation},
     author = {Peng, Ru and Zou, Heming and Wang, Haobo and Zeng, Yawen and Huang, Zenan and Zhao, Junbo},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024},
     dimensions = {true},
   }

9. Qwen1.5 Blog

   

   Introducing qwen1. 5

   Qwen Team

   Online Blog, Apr 2024

   Bib PDF Code

   @article{team2024introducing,
     title = {Introducing qwen1. 5},
     author = {Team, Qwen},
     journal = {Online Blog},
     year = {2024},
     dimensions = {true},
   }

2023

1. ICCV 2023

   

   Came: Contrastive automated model evaluation

   Ru Peng , Qiuyang Duan, Haobo Wang, Jiachen Ma, Yanbo Jiang, Yongjun Tu, Xiu Jiang, and Junbo Zhao

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, Apr 2023

   Bib PDF Code

   @inproceedings{peng2023came,
     title = {Came: Contrastive automated model evaluation},
     author = {Peng, Ru and Duan, Qiuyang and Wang, Haobo and Ma, Jiachen and Jiang, Yanbo and Tu, Yongjun and Jiang, Xiu and Zhao, Junbo},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {20121--20132},
     year = {2023},
     dimensions = {true},
   }

2. ArXiv 2023

   

   Better Sign Language Translation with Monolingual Data

   Ru Peng , Yawen Zeng, and Junbo Zhao

   arXiv preprint arXiv:2304.10844, Apr 2023

   Bib PDF Code

   @article{peng2023better,
     title = {Better Sign Language Translation with Monolingual Data},
     author = {Peng, Ru and Zeng, Yawen and Zhao, Junbo},
     journal = {arXiv preprint arXiv:2304.10844},
     year = {2023},
     dimensions = {true},
   }

2022

1. EMNLP 2022 Oral

   

   Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation

   Ru Peng , Yawen Zeng, and Junbo Zhao

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Apr 2022

   Bib PDF Code

   @inproceedings{peng2022distill,
     title = {Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation},
     author = {Peng, Ru and Zeng, Yawen and Zhao, Junbo},
     booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
     pages = {2379--2390},
     year = {2022},
     dimensions = {true},
   }

2. ICONIP 2022 Oral

   

   Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network

   Ru Peng , Nankai Lin, Yi Fang, Shengyi Jiang, Tianyong Hao, Boyu Chen, and Junbo Zhao

   In International Conference on Neural Information Processing, Apr 2022

   Bib PDF Code

   @inproceedings{peng2022deps,
     title = {Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network},
     author = {Peng, Ru and Lin, Nankai and Fang, Yi and Jiang, Shengyi and Hao, Tianyong and Chen, Boyu and Zhao, Junbo},
     booktitle = {International Conference on Neural Information Processing},
     pages = {26--37},
     year = {2022},
     organization = {Springer},
     dimensions = {true},
   }

3. ICMR 2022 Oral

   

   Hybridvocab: Towards multi-modal machine translation via multi-aspect alignment

   Ru Peng , Yawen Zeng, and Junbo Zhao

   In Proceedings of the 2022 International Conference on Multimedia Retrieval, Apr 2022

   Bib PDF Code

   @inproceedings{peng2022hybridvocab,
     title = {Hybridvocab: Towards multi-modal machine translation via multi-aspect alignment},
     author = {Peng, Ru and Zeng, Yawen and Zhao, Junbo},
     booktitle = {Proceedings of the 2022 International Conference on Multimedia Retrieval},
     pages = {380--388},
     year = {2022},
     dimensions = {true},
   }

2021

1. NCA 2021

   

   Syntax-aware neural machine translation directed by syntactic dependency degree

   Ru Peng , Tianyong Hao, and Yi Fang

   Neural Computing and Applications, Apr 2021

   Bib PDF

   @article{peng2021syntax,
     title = {Syntax-aware neural machine translation directed by syntactic dependency degree},
     author = {Peng, Ru and Hao, Tianyong and Fang, Yi},
     journal = {Neural Computing and Applications},
     volume = {33},
     number = {23},
     pages = {16609--16625},
     year = {2021},
     publisher = {Springer},
     dimensions = {true},
   }

2019

1. CCMT 2019 Best Paper Candidates

   

   Neural machine translation with attention based on a new syntactic branch distance

   Ru Peng , Zhitao Chen, Tianyong Hao, and Yi Fang

   In Machine Translation: 15th China Conference, CCMT 2019, Nanchang, China, September 27–29, 2019, Revised Selected Papers 15, Apr 2019

   Bib PDF

   @inproceedings{peng2019neural,
     title = {Neural machine translation with attention based on a new syntactic branch distance},
     author = {Peng, Ru and Chen, Zhitao and Hao, Tianyong and Fang, Yi},
     booktitle = {Machine Translation: 15th China Conference, CCMT 2019, Nanchang, China, September 27--29, 2019, Revised Selected Papers 15},
     pages = {47--57},
     year = {2019},
     organization = {Springer},
     dimensions = {true},
   }