publications

2026

1. EMNLP

   

   Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

   Yanting Yang^*, Can Jin^* , Jinman Zhao, Jiahao Wu, Yang Zhou , Zhepeng Wang , Zhendong Wang , Mu Zhou, and Dimitris N. Metaxas

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

   PDF

   @inproceedings{yang2026act,
     title = {Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents},
     author = {Yang, Yanting and Jin, Can and Zhao, Jinman and Wu, Jiahao and Zhou, Yang and Wang, Zhepeng and Wang, Zhendong and Zhou, Mu and Metaxas, Dimitris N.},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
     year = {2026},
     url = {https://arxiv.org/abs/2609.02042},
   }

2. arXiv

   

   DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation

   Yang Zhou^*, Can Jin^*, Zihan Dong , Zhepeng Wang, Yanting Yang, Shiyu Zhao , Lei Li, Runxue Bao, Yaochen Xie, and Dimitris N. Metaxas

   2026

   PDF Code

   @misc{zhou2026dare,
     title = {DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation},
     author = {Zhou, Yang and Jin, Can and Dong, Zihan and Wang, Zhepeng and Yang, Yanting and Zhao, Shiyu and Li, Lei and Bao, Runxue and Xie, Yaochen and Metaxas, Dimitris N.},
     year = {2026},
     journal = {arXiv preprint arXiv:2605.09188},
   }

3. ICML · AI4Math

   

   Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

   Can Jin^* , Jiakang Li^*, Rui Wu , Eddy Z. Zhang^†, and Dimitris N. Metaxas^†

   In 3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents, 2026

   PDF Code

   @inproceedings{jin2026weak,
     title = {Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight},
     author = {Jin, Can and Li, Jiakang and Wu, Rui and Zhang, Eddy Z. and Metaxas, Dimitris N.},
     booktitle = {3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents},
     year = {2026},
     url = {https://openreview.net/forum?id=oEfedgUChS},
   }

4. ICML

   

   DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training

   Can Jin^*, Hongwu Peng^*, Mingcan Xiang, Qixin Zhang, Xiangchi Yuan, Amit Hasan, Ohiremen Dibua, Yifan Gong, Yan Kang^†, and Dimitris N. Metaxas^†

   In Forty-third International Conference on Machine Learning, 2026

   PDF

   @inproceedings{jin2025dtopp,
     title = {DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training},
     author = {Jin, Can and Peng, Hongwu and Xiang, Mingcan and Zhang, Qixin and Yuan, Xiangchi and Hasan, Amit and Dibua, Ohiremen and Gong, Yifan and Kang, Yan and Metaxas, Dimitris N.},
     booktitle = {Forty-third International Conference on Machine Learning},
     year = {2026},
   }

5. ACL

   

   Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety

   Can Jin^*, Rui Wu^*, Tong Che^*, Qixin Zhang, Hongwu Peng , Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han , Zhao Zhang, Yuan Cao, Ruixiang Tang^†, and Dimitris N. Metaxas^†

   In The 64th Annual Meeting of the Association for Computational Linguistics, 2026

   PDF

   @inproceedings{jin2026reasoning,
     title = {Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety},
     author = {Jin, Can and Wu, Rui and Che, Tong and Zhang, Qixin and Peng, Hongwu and Zhao, Jiahui and Wang, Zhenting and Wei, Wenqi and Han, Ligong and Zhang, Zhao and Cao, Yuan and Tang, Ruixiang and Metaxas, Dimitris N.},
     booktitle = {The 64th Annual Meeting of the Association for Computational Linguistics},
     year = {2026},
   }

6. EMNLP

   

   Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

   Can Jin, Hongwu Peng, Qixin Zhang, Yang Zhou , Yujin Tang, Tong Che^†, and Dimitris N. Metaxas^†

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

   PDF Code

   @inproceedings{jin2025two,
     title = {Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning},
     author = {Jin, Can and Peng, Hongwu and Zhang, Qixin and Zhou, Yang and Tang, Yujin and Che, Tong and Metaxas, Dimitris N.},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
     year = {2026},
     url = {https://arxiv.org/abs/2504.09772},
   }

7. EMNLP

   

   Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

   Jiakang Li^*, Guanyu Zhu^*, Can Jin^* , Chenxi Huang, Dexu Yu , Ronghao Chen, Yang Zhou, Hongwu Peng, Xuanqi Lan, Dimitris N. Metaxas^† , and Youhua Li^†

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

   PDF Code

   @inproceedings{li2026latent,
     title = {Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs},
     author = {Li, Jiakang and Zhu, Guanyu and Jin, Can and Huang, Chenxi and Yu, Dexu and Chen, Ronghao and Zhou, Yang and Peng, Hongwu and Lan, Xuanqi and Metaxas, Dimitris N. and Li, Youhua},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
     year = {2026},
     url = {https://arxiv.org/abs/2606.00726},
   }

8. CVPR

   

   Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models

   Jingchen Sun , Shaobo Han, Deep Patel, Wataru Kohno, Can Jin , and Changyou Chen

   In The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

   PDF

   @inproceedings{sun2026uncertainty,
     title = {Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models},
     author = {Sun, Jingchen and Han, Shaobo and Patel, Deep and Kohno, Wataru and Jin, Can and Chen, Changyou},
     booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     year = {2026},
   }

9. ICML

   

   Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals

   Zihan Dong , Zhixian Zhang, Yang Zhou, Can Jin, Ruijia Wu , and Linjun Zhang

   In Forty-third International Conference on Machine Learning, 2026

   PDF

   @inproceedings{dong2026evaluating,
     title = {Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals},
     author = {Dong, Zihan and Zhang, Zhixian and Zhou, Yang and Jin, Can and Wu, Ruijia and Zhang, Linjun},
     booktitle = {Forty-third International Conference on Machine Learning},
     year = {2026},
   }

10. CVPR

    

    Led: Llm enhanced open-vocabulary object detection without human curated data generation

    Yang Zhou, Shiyu Zhao , Yuxiao Chen, Zhenting Wang, Can Jin, and Dimitris N Metaxas

    In The IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings, 2026

    PDF

    @inproceedings{zhou2025led,
      title = {Led: Llm enhanced open-vocabulary object detection without human curated data generation},
      author = {Zhou, Yang and Zhao, Shiyu and Chen, Yuxiao and Wang, Zhenting and Jin, Can and Metaxas, Dimitris N},
      booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings},
      year = {2026},
    }

2025

1. ICLR

   

   LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

   Can Jin , Ying Li , Mingyu Zhao, Shiyu Zhao, Zhenting Wang, Xiaoxiao He, Ligong Han, Tong Che, and Dimitris N. Metaxas

   In The Thirteenth International Conference on Learning Representations, 2025

   PDF Code

   @inproceedings{jin2025lorvp,
     title = {LoR-{VP}: Low-Rank Visual Prompting for Efficient Vision Model Adaptation},
     author = {Jin, Can and Li, Ying and Zhao, Mingyu and Zhao, Shiyu and Wang, Zhenting and He, Xiaoxiao and Han, Ligong and Che, Tong and Metaxas, Dimitris N.},
     booktitle = {The Thirteenth International Conference on Learning Representations},
     year = {2025},
     url = {https://openreview.net/forum?id=5btFIv2PNb},
   }

2. AAAI

   

   Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

   Can Jin^*, Tianjin Huang^* , Yihua Zhang, Mykola Pechenizkiy, Sijia Liu , Shiwei Liu, and Tianlong Chen

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

   PDF Code

   @inproceedings{jin2025visual,
     title = {Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective},
     author = {Jin, Can and Huang, Tianjin and Zhang, Yihua and Pechenizkiy, Mykola and Liu, Sijia and Liu, Shiwei and Chen, Tianlong},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {39},
     number = {4},
     pages = {4111--4119},
     year = {2025},
     url = {https://arxiv.org/pdf/2312.01397},
   }

3. WWW · RelWeb

   

   APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking (Best Paper Award @ RelWeb)

   Can Jin^*, Hongwu Peng^*, Shiyu Zhao, Zhenting Wang, Wujiang Xu, Ligong Han , Jiahui Zhao, Kai Zhong, Sanguthevar Rajasekaran, and Dimitris N Metaxas

   In Companion Proceedings of the ACM Web Conference 2025, Sydney, NSW, Australia, 2025

   DOI PDF Code

   @inproceedings{jin2025apeer,
     title = {APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking (<span class="award">Best Paper Award @ RelWeb</span>)},
     author = {Jin, Can and Peng, Hongwu and Zhao, Shiyu and Wang, Zhenting and Xu, Wujiang and Han, Ligong and Zhao, Jiahui and Zhong, Kai and Rajasekaran, Sanguthevar and Metaxas, Dimitris N},
     booktitle = {Companion Proceedings of the ACM Web Conference 2025},
     location = {Sydney, NSW, Australia},
     series = {WWW '25},
     year = {2025},
     doi = {10.1145/3701716.3717574},
     isbn = {979-8-4007-1331-6/2025/04},
     url = {https://arxiv.org/abs/2406.14449},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     keywords = {Prompt engineering, Information Retrieval, Large Language Model, ReRanking},
   }

4. ACM MM

   

   Graph Canvas for Controllable 3D Scene Generation

   Libin Liu , Shen Chen, Sen Jia, Jingzhe Shi, Can Jin, Zongkai Wu, Jenq-Neng Hwang , and Lei Li

   In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, 2025

   DOI PDF

   @inproceedings{liu2025graph,
     author = {Liu, Libin and Chen, Shen and Jia, Sen and Shi, Jingzhe and Jin, Can and Wu, Zongkai and Hwang, Jenq-Neng and Li, Lei},
     title = {Graph Canvas for Controllable 3D Scene Generation},
     year = {2025},
     isbn = {9798400720352},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3746027.3754554},
     doi = {10.1145/3746027.3754554},
     booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
     pages = {2536–2545},
     numpages = {10},
     keywords = {3d generation, graph representation, multimodal large language model, spatial intelligence},
     location = {Dublin, Ireland},
     series = {MM '25},
   }

5. NeurIPS

   

   Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

   Qixin Zhang, Yan Sun, Can Jin , Xikun ZHANG, Yao Shu , Puning Zhao, Li Shen, and Dacheng Tao

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

   PDF Poster

   @inproceedings{zhang2025effective,
     title = {Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives},
     author = {Zhang, Qixin and Sun, Yan and Jin, Can and ZHANG, Xikun and Shu, Yao and Zhao, Puning and Shen, Li and Tao, Dacheng},
     booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems},
     year = {2025},
     url = {https://openreview.net/forum?id=isAYKdLwtB},
   }

6. ICML

   

   Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints

   Qixin Zhang , Wei Huang, Can Jin , Puning Zhao, Yao Shu, Li Shen, and Dacheng Tao

   In Forty-second International Conference on Machine Learning, 2025

   PDF Poster

   @inproceedings{zhang2025multinoulli,
     title = {Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints},
     author = {Zhang, Qixin and Huang, Wei and Jin, Can and Zhao, Puning and Shu, Yao and Shen, Li and Tao, Dacheng},
     booktitle = {Forty-second International Conference on Machine Learning},
     year = {2025},
     url = {https://openreview.net/forum?id=6XQOarhYF8},
   }

2024

1. NeurIPS

   

   Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate

   Can Jin^*, Tong Che^*, Hongwu Peng^†, Yiyuan Li^†, Dimitris Metaxas^‡, and Marco Pavone^‡

   In Advances in Neural Information Processing Systems, 2024

   PDF Code Poster Website

   @inproceedings{jin2024lot,
     author = {Jin, Can and Che, Tong and Peng, Hongwu and Li, Yiyuan and Metaxas, Dimitris and Pavone, Marco},
     booktitle = {Advances in Neural Information Processing Systems},
     editor = {Globerson, A. and Mackey, L. and Belgrave, D. and Fan, A. and Paquet, U. and Tomczak, J. and Zhang, C.},
     pages = {966--994},
     publisher = {Curran Associates, Inc.},
     title = {Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate},
     url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/01ce1ae7f94d139e4917f9e4425a4f38-Paper-Conference.pdf},
     volume = {37},
     year = {2024},
   }