publications

publications by categories in reversed chronological order.

2026

  1. CVPR2026
    CodePercept: Code-Grounded Visual STEM Perception for MLLMs
    Tongkun Guan, Zhibo Yang, Jianqiang Wan, Mingkun Yang, Zhengtao Guo, Zijian Hu, Ruilin Luo, Ruize Chen, and 5 more authors
    CVPR2026, 2026
    Paper Code
  2. TIP2026
    BPE-Level Visual-Textual Alignment for Multi-Scene Text Retrieval
    Tongkun Guan, Yutong Cai, Haocheng Wang, Zijian Hu, Wei Shen, and Xiaokang Yang
    TIP, 2026
    Paper
  3. ECCV2026
    AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking
    Zining Wang*, Tongkun Guan*, Boming Chen*, Zhentao Guo, Jianqiang Liu, Chao Jin, Chen Duan, Kai Zhou, and 3 more authors
    ECCV, 2026
    Paper
  4. ECCV2026
    ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering
    Zhentao Guo*, Chen Duan*, Tongkun Guan*, Zining Wang, Kai Zhou, and Pengfei Yan
    ECCV, 2026
    Paper Code
  5. ECCV2026
    LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement
    Tongkun Guan*, Haocheng Wang*, Wei Shen, and Xiaokang Yang
    ECCV, 2026
    Paper
  6. ICLR2026
    From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
    Ruilin Luo, Chufan Shi, Yizhen Zhang, Cheng Yang, Songtao Jiang, Tongkun Guan, Ruizhe Chen, Ruihang Chu, and 5 more authors
    ICLR, 2026
    Paper
  7. CVPR2026
    Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
    Songtao Jiang, Sibo Song, Chenyi Zhou, Yuan Wang, Ruizhe Chen, Tongkun Guan, Ruilin Luo, Yan Zhang, and 7 more authors
    CVPR, 2026
    Paper Code

2025

  1. ICCV2025
    A Token-level Text Image Foundation Model for Document Understanding
    Tongkun Guan, Zining Wang, Pei Fu, Zhengtao Guo, Wei Shen, Kai Zhou, Tiezhu Yue, Chen Duan, and 3 more authors
    ICCV, 2025
    Paper Code demo project_page
  2. CVPR2025
    Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
    Zining Wang*, Tongkun Guan*, Pei Fu, Wei Shen, and Xiaokang Yang
    CVPR, 2025
    Paper Code
  3. TPAMI2025
    CCDPlus: Towards Accurate Character to Character Distillation for Text Recognition
    Tongkun Guan, Wei Shen, and Xiaokang Yang
    TPAMI, 2025
    Paper Code
  4. ACL2025
    Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
    Pei Fu, Tongkun Guan, Zining Wang, Zhentao Guo, Chen Duan, Hao Sun, Boming Chen, Jiayao Ma, and 3 more authors
    ACL2025, 2025
    Paper

2024

  1. ECCV2024
    Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
    Tongkun Guan, Wei Shen, Xue Yang, Xuehui Wang, and Xiaokang Yang
    ECCV, 2024
    Paper Code
  2. ECCV2024
    PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
    Tongkun Guan, Chengyu Lin, Wei Shen, and Xiaokang Yang
    ECCV, 2024
    Paper Code

2023

  1. CVPR2023
    Self-supervised Implicit Glyph Attention for Text Recognition
    Tongkun Guan, Chaochen Gu, Jingzheng Tu, Xue Yang, Qi Feng, Yudi Zhao, Xiaokang Yang, and Wei Shen
    CVPR, 2023
    Paper Blog Code Poster
  2. ICCV2023
    Self-supervised Character-to-Character Distillation for Text Recognition
    Tongkun Guan, Wei Shen, Xue Yang, Qi Feng, Zekun Jiang, and Xiaokang Yang
    ICCV, 2023
    Paper Blog Code Poster

2022

  1. TCSVT
    Industrial scene text detection with refined feature-attentive network
    Tongkun Guan, Chaochen Gu, Changsheng Lu, Jingzheng Tu, Qi Feng, Kaijie Wu, and Xinping Guan
    IEEE Transactions on Circuits and Systems for Video Technology, 2022
    Paper Code Poster Dataset

2021

  1. TIM
    Crossover structure separation with application to neuron tracing in volumetric images
    Changhao Guo, Min Liu, Tongkun Guan, Weixun Chen, He Wen, Tieyong Zeng, and Yaonan Wang
    IEEE Transactions on Instrumentation and Measurement, 2021
    Paper DOI: https://doi.org/10.1109/TIM.2021.3072119