Yuan Zhang Ph.D. Candidate Center on Frontiers of Computing Studies, Peking University Email: zhangyuan [at] alumni.pku.edu.cn

Biography

His major research interests lie within efficient machine learning algorithms, like

• Efficient AI (KD, Pruning, Quantization)
• Multimodal Large Language Model

Education

Peking University (PKU), Beijing, China PhD Candidate at Center on Frontiers of Computing Studies. Sep. 2024 – Jun. 2028 Rank: 5/52 Research: Efficiency for Multimodal Large Language Model

Peking University (PKU), Beijing, China Master Degree. Sep. 2020 – Jun. 2023 Rank: 3/110 National Scholarship of China

Hohai University (HHU), Nanjing, China Bachelor Degree. Sep. 2016 – Jun. 2020 Rank: 1/112 National Scholarship of China

Selected Publications

• C1SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
  Yuan Zhang, ChunKai Fan, Junpeng Ma, and 7 more authors, Shanghang Zhang
  International Conference on Machine Learning (ICML), 2025.

  PDF Bib Code Panasonic Press

• C2Unveiling the Tapestry of Consistency in Large Vision-Language Models
  Yuan Zhang, Fei Xiao, Tao Huang, and 6 more authors, Haoyuan Guo
  Advances in Neural Information Processing Systems (NeurIPS), 2024.

  PDF Bib Code Video ByteDance Seed Press

• C3FreeKD: Knowledge Distillation via Semantic Frequency Prompt
  Yuan Zhang, Tao Huang, Jiaming Liu, Tao Jiang, Kuan Cheng, Shanghang Zhang
  Computer Vision and Pattern Recognition (CVPR), 2024.

  PDF Bib Code

• C4Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty
  Yuan Zhang, Weihua Chen, Yichen Lu, Tao Huang, Xiuyu Sun, Jian Cao
  ACM International Conference on Multimedia (ACM MM), 2023.

  PDF Bib Code Video

• C5Distilling Cross-Modal Knowledge via Feature Disentanglement
  Junhong Liu, Yuan Zhang, Tao Huang, Wenchao Xu, Renyu Yang
  AAAI Conference on Artificial Intelligence (AAAI), 2025.

  PDF Bib Code

• C6MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
  Jiajun Cao, Yuan Zhang, Tao Huang, Ming Lu, Qizhe Zhang, Ruichuan An, Ningning Ma, Shanghang Zhang
  Computer Vision and Pattern Recognition (CVPR), 2025.

  PDF Bib Code

• C7Knowledge Diffusion for Distillation
  Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Chang Xu
  Advances in Neural Information Processing Systems (NeurIPS), 2023.

  PDF Bib Code

• C8Masked Distillation with Receptive Tokens
  Tao Huang*, Yuan Zhang*, Shan You, Fei Wang, Chen Qian, Jian Cao, Chang Xu
  International Conference on Learning Representations (ICLR), 2023.

  PDF Bib Code Video

Manuscripts

• ResearchSparseVLM+: Visual Token Sparsification with Improved Text-Visual Attention Pattern
  Yuan Zhang, Junpeng Ma, Qizhe Zhang, Chun-Kai Fan, Wenzhao Zheng, Kuan Cheng, Jiwen Lu, Shanghang Zhang
  ResearchGate preprint (2025).

  PDF Bib Code

• arXivChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
  Yuan Zhang, Ming Lu, Junwen Pan, Tao Huang, Kuan Cheng, Qi She, Shanghang Zhang
  arXiv preprint arXiv:2511.17106 (2025).

  PDF Bib

• arXivLoss-Oriented Ranking for Automated Visual Prompting in LVLMs
  Yuan Zhang, Chun-Kai Fan, Tao Huang, Ming Lu, Sicheng Yu, Junwen Pan, Kuan Cheng, Qi She, Shanghang Zhang
  arXiv preprint arXiv:2506.16112 (2025).

  PDF Bib

• arXivDAMO-YOLO: A Report on Real-Time Object Detection Design
  Xianzhe Xu*, Yiqi Jiang*, Weihua Chen*, Yilun Huang*, Yuan Zhang*, Xiuyu Sun
  arXiv preprint arXiv:2211.15444 (2022).

  PDF Bib Code Video

Research Experience

Berkeley Artificial Intelligence Research Lab (BAIR), California, USA Remote Research Intern (Advisor: Wenzhao Zheng). Sep. 2024 – Dec. 2024 Vision Foundation Model. Efficiency in LVLMs and propose SparseVLM.

ByteDance Seed Foundation Model, Beijing, China (S1) Researcher (Advisor: Haoyuan Guo). (S2) Research Intern (Advisor: Ming Lu). Jul. 2023 – Jul. 2024, Jan. 2025 – Now Vision Foundation Model. Research on Consistency in LVLMs and propose ConBench.

Alibaba DAMO Academy, Beijing, China Research Intern (Advisor: Weihua Chen). Jun. 2022 – Feb. 2023 Research on knowledge distillation (KD) and propose AvatarKD. Distill for DAMO-YOLO.

SenseTime Research, Beijing, China Research Intern (Advisor: Tao Huang). Mar. 2022 – Jun. 2022 Research on knowledge distillation (KD) and propose MasKD. Develop on MMRazor.

Academic Services

• CVPR 2024 | ECCV 2024 | ACM MM 2024 | NeurIPS 2024
• ICLR 2025 | AISTATS 2025 | CVPR 2025 | ICML 2025 | ICCV 2025 | NeurIPS 2025
• WACV 2026 | AAAI 2026 | AISTATS 2026 | ICLR 2026 | CVPR 2026 | ICML 2026

• IJCV | T-IP | T-MLR | T-MM |T-CSVT | T-NNLS

Open Source Projects

• YOLOv5-Multibackbone-Compression
  
  Duty: Owner.

  Oct. 2021 – Mar. 2022
  Description: YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantization (MQBench) and Deployment (TensorRT, ncnn) Compression Tool Box.
  
• DAMO-YOLO
  
  Duty: Distill and Deployment.

  Jun. 2022 – Sep. 2022
  Description: First make distillation great again on all size models of YOLO series (1.0 AP+), especially on the small size.
  

Awards and Honor

• Tencent Scholarship
  
  Ph.D. period (¥ 20,000).

  Sep. 2025
• National Scholarship of China
  
  Master period (¥ 20,000).

  Nov. 2021
• National Scholarship of China
  
  Undergraduate period (¥ 8,000).

  Nov. 2018

Visitors