avatar

赵烜乐
Xuanle Zhao

Ph.D. Student
Institute of Automation, Chinese Academy of Sciences



About Me

Hello! I am a fourth-year Ph.D. student at the Institute of Automation, Chinese Academy of Sciences (CASIA), under the supervision of Bo Xu and Xinyuan Cai. My research interests include Multimodal Code Generation and AI for Science. Prior to that, I received my B.S. degree from University of Electronic Science and Technology of China (UESTC) in 2022. Currently, I am a research intern at Moonshot AI. My current research mainly focuses on visual coding agents for scenarios such as web, game, and SVG generation.

I expect to graduate in Summer 2027 and am currently seeking research or engineering positions related to LLMs.

News

Publications (Selected, * Equal contribution)

  1. Kimi K2.6: Advancing Open-Source Coding
    Xuanle Zhao, contributor to WebDev Agents
    Moonshot AI
    Blog Model   Technical Blog

  2. TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
    Deyang Jiang*, Jing Huang*, Xuanle Zhao*, Lei Chen, Liming Zheng, Fanfan Liu, Haibo Qiu, Peng Shi, Zhixiong Zeng
    The 43rd International Conference on Machine Learning
    Code arXiv   ICML'26

  3. ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding
    Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Xiuyi Chen, Bo Xu
    Findings of the 64th Annual Meeting of the Association for Computational Linguistics
    Code arXiv   ACL'26 Findings

  4. OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward
    Haoyue Yang*, Xuanle Zhao*, Xuexin Liu*, Feibang Jiang, Yao Zhu
    Findings of the 64th Annual Meeting of the Association for Computational Linguistics
    Code arXiv   ACL'26 Findings

  5. AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
    Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
    The 64th Annual Meeting of the Association for Computational Linguistics
    Code arXiv   ACL'26

  6. OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
    Yufeng Zhong*, Lei Chen*, Xuanle Zhao*, Wenkang Han, Liming Zheng, Jing Huang, Deyang Jiang, Yilin Cao, Lin Ma, Zhixiong Zeng
    arXiv preprint, 2026.
    Code arXiv   OCR Report

  7. Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
    Yufeng Zhong*, Lei Chen*, Zhixiong Zeng, Xuanle Zhao, Deyang Jiang, Liming Zheng, Jing Huang, Haibo Qiu, Peng Shi, Siqi Yang, Lin Ma
    The 43rd IEEE/CVF Conference on Computer Vision and Pattern Recognition
    Code arXiv   CVPR'26

  8. VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
    Xuanle Zhao, Deyang Jiang, Zhixiong Zeng, Lei Chen, Haibo Qiu, Jing Huang, Yufeng Zhong, Liming Zheng, Yilin Cao, Lin Ma
    arXiv preprint, 2025.
    Code arXiv   arXiv

  9. Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
    Lei Chen, Xuanle Zhao, Zhixiong Zeng, Jing Huang, Liming Zheng, Yufeng Zhong, Lin Ma
    The 14th International Conference on Learning Representations
    Code arXiv   ICLR'26

  10. TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
    Xuanle Zhao, Shuxin Zeng, Xinyuan Cai, Xiang Cheng, Duzhen Zhang, Xiuyi Chen, Bo Xu
    The 40th AAAI Conference on Artificial Intelligence
    Code arXiv   AAAI'26

  11. ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing
    Xuanle Zhao*, Xuexin Liu*, Haoyue Yang*, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, Chi Chen
    Findings of the 63rd Annual Meeting of the Association for Computational Linguistics
    Code arXiv   ACL'25 Findings

  12. ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
    Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu, Maosong Sun
    The 63rd Annual Meeting of the Association for Computational Linguistics
    Code arXiv   ACL'25

  13. ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
    Xuanle Zhao, Duzhen Zhang, Liyuan Han, Tielin Zhang, Bo Xu
    The 37th Conference on Neural Information Processing Systems
    Code arXiv   NeurIPS'23

Internships

Education


Powered by Jekyll and Minimal Light theme.