Yang Li (郦洋)

@inproceedings{dong2026flowtracer,
  title = {How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs},
  author = {Dong*, Zhichen and Li*, Yang and Sun, Yuhan and Wang, Weixun and Luo, Yijia and Peng, Zinian and Su, Wenbo and Yu, Cheng and Zheng, Bo and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2026}
}

@inproceedings{li2026attention,
  title = {Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization},
  author = {Li, Yang and Dong, Zhichen and Sun, Yuhan and Wang, Weixun and Xiong, Shaopan and Luo, Yijia and Liu, Jiashun and Lu, Han and Wang, Jiamang and Su, Wenbo and Zheng, Bo and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2026}
}

@inproceedings{long2026reasoning,
  title = {Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs},
  author = {Long*, Rujiao and Li*, Yang and Zhang, Xingyao and Wang, Weixun and Lin, Tianqianjin and Zhao, Xi and Xu, Yuchi and Su, Wenbo and Yan, Junchi and Zheng, Bo},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year = {2026}
}

@inproceedings{chen2026maskco,
  title = {MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization},
  author = {Chen*, Lvda and Li*, Yang and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2026}
}

@inproceedings{guo2026conrep,
  title = {ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types},
  author = {Guo, Ziao and Li, Yang and Wang, Shiyue and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2026}
}

@inproceedings{wang2026native,
  title = {Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization},
  author = {Wang, Yu and Li, Yang and Ma, Jiale and Yan, Junchi and Chang, Yi},
  booktitle = {International Conference on Learning Representations},
  year = {2026}
}

@misc{rome2026letitflow,
  title = {Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem},
  author = {{ROCK and ROLL and IFLOW and DT Joint Team}},
  note = {Core contributor},
  year = {2026}
}

@misc{lu2025rollflash,
  title = {Part II: ROLL Flash--Accelerating RLVR and Agentic Training with Asynchrony},
  author = {Lu, Han and Liu, Zichen and Xiong, Shaopan and He, Yancheng and Gao, Wei and Wu, Yanan and Wang, Weixun and Liu, Jiashun and Li, Yang and Zhao, Haizhou and Huang, Ju and Yang, Siran and Li, Xiaoyang and Luo, Yijia and Liu, Zihe and Pan, Ling and Yan, Junchi and Wang, Wei and Su, Wenbo and Wang, Jiamang and Qu, Lin and Zheng, Bo},
  year = {2025}
}

@inproceedings{zheng2025crypto,
  title = {Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks},
  author = {Zheng, Xinhao and Song, Xinhao and Qiu, Bolin and Li, Yang and Gui, Zhongteng and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025}
}

@inproceedings{li2025gensco,
  title = {Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization},
  author = {Li, Yang and Chen, Lvda and Wang, Haonan and Wang, Runzhong and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025}
}

@inproceedings{wang2025strudico,
  title = {StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization},
  author = {Wang, Yu and Li, Yang and Yan, Junchi and Chang, Yi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025}
}

@inproceedings{ma2025mlcobench,
  title = {ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs},
  author = {Ma, Jiale and Pan, Wenzheng and Li, Yang and Yan, Junchi},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year = {2025},
}

@inproceedings{li2025pcl,
  title = {Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning},
  author = {Li, Yang and Ma, Jiale and Yang, Yebin and Wu, Qitian and Zha, Hongyuan and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2025}
}

@inproceedings{ma2025coexpander,
  title = {COExpander: Adaptive Solution Expansion for Combinatorial Optimization},
  author = {Ma, Jiale and Pan, Wenzheng and Li, Yang and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2025}
}

@inproceedings{li2025ml4tsp,
  title = {Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search},
  author = {Li, Yang and Ma, Jiale and Pan, Wenzheng and Wang, Runzhong and Geng, Haoyu and Yang, Nianzu and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2025}
}

@inproceedings{pan2025unico,
  author = {Pan, Wenzheng and Xiong, Hao and Ma, Jiale and Zhao, Wentao and Li, Yang and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2025}
}

@inproceedings{li2024fastt2t,
  title = {Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization},
  author = {Li*, Yang and Guo*, Jinpei and Wang, Runzhong and Zha, Hongyuan and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024}
}

@inproceedings{zheng2024learning,
  title = {Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation},
  author = {Zheng, Xinhao and Li, Yang and Fan, Cunxin and Wu, Huaijin and Song, Xinhao and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024}
}

@inproceedings{geng2024rethinking,
  title = {Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime},
  author = {Geng, Haoyu and Ruan, Hang and Wang, Runzhong and Li, Yang and Wang, Yang and Chen, Lei and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024}
}

@article{wang2024learning,
  title = {Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks},
  author = {Wang, Runzhong and Li, Yang and Yan, Junchi and Yang, Xiaokang},
  journal = {SCIENTIA SINICA Informationis 2024},
  year = {2024}
}

@inproceedings{guo2024acm,
  title = {ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation},
  author = {Guo, Ziao and Li, Yang and Liu, Chang and Ouyang, Wenli and Yan, Junchi},
  booktitle = {The Forty-first International Conference on Machine Learning},
  year = {2024},
}

@inproceedings{chen2024mixsat,
  title = {MixSATGEN: Learning Graph Mixing for SAT Instance Generation},
  author = {Chen*, Xinyan and Li*, Yang and Wang, Runzhong and Yan, Junchi},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
}

@article{li2024machine,
  title = {Machine Learning Insides OptVerse AI Solver: Design Principles and Applications},
  author = {Li, Xijun and Zhu, Fangzhou and Zhen, Hui-Ling and Luo, Weilin and Lu, Meng and Huang, Yimin and Fan, Zhenan and Zhou, Zirui and Kuang, Yufei and Wang, Zhihai and Geng, Zijie and Li, Yang and Liu, Haoyang and An, Zhiwu and Yang, Muming and Li, Jianshu and Wang, Jie and Yan, Junchi and Sun, Defeng and Zhong, Tao and Zhang, Yong and Zeng, Jia and Yuan, Mingxuan and Hao, Jianye and Yao, Jun and Mao, Kun},
  year = {2024},
  journal = {arXiv preprint},
}

@inproceedings{yang2024molecule,
  title = {Molecule Generation for Drug Design: a Graph Learning Perspective},
  author = {Yang, Nianzu and Wu, Huaijin and Zeng, Kaipeng and Li, Yang and Yan, Junchi},
  year = {2024},
  booktitle = {Fundamental Research},
}

@inproceedings{li2023t2tco,
  title = {T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization},
  author = {Li, Yang and Guo, Jinpei and Wang, Runzhong and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2023}
}

@inproceedings{li2023hardsatgen,
  title = {HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline},
  author = {Li, Yang and Chen, Xinyan and Guo, Wenxuan and Li, Xijun and Luo, Wanqian and Huang, Junhua and Zhen, Hui-Ling and Yuan, Mingxuan and Yan, Junchi},
  booktitle = {Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  year = {2023}
}

@inproceedings{iid2023li,
  author = {Li*, Yang and Shi*, Liangliang and Yan, Junchi},
  booktitle = {Proceedings of the 32nd International Joint Conference on Artificial Intelligence},
  title = {IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse},
  year = {2023}
}

@inproceedings{li2022improving,
  author = {Li, Yang and Mo, Yichuan and Shi, Liangliang and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.},
  pages = {8868--8881},
  publisher = {Curran Associates, Inc.},
  title = {Improving Generative Adversarial Networks via Adversarial Learning in Latent Space},
  volume = {35},
  year = {2022}
}