Junyan Li

I am a third-year PhD student in computer science at the University of Massachusetts Amherst, working with Prof. Chuang Gan. Previously, I completed my undergraduate studies at Zhejiang University and the University of Illinois Urbana-Champaign. I also have been interned in Apple, NVIDIA and Microsoft Research Asia, etc.

I am interested in building efficient and reliable foundation model systems for real-world applications. My research primarily focuses on model development, while also exploring system-level efficiency through system–model co-design.

Outside of research, I enjoy cooking, photography, snowboarding, and bouldering. I also have a (very very) lovely cat named 汤圆 (pronounced “tahng-ywen”), who keeps me good company.

Email  /  Google Scholar  /  Github

profile photo

News

  • [2026.04] Budget Guidance is accepted by ACL 2026 Findings.
  • [2025.05] CommVQ is accepted by ICML 2025.
  • [2024.08] FlexAttention is accepted by ECCV 2024.
  • [2024.01] CoVLM is accepted by ICLR 2024.
  • [2023.07] EfficientViT is accepted by ICCV 2023.
  • [2023.06] ToP is accepted by KDD 2023.
  • [2023.03] ProxylessGaze is publicly available as an application of ProxylessNAS. It is an open-source gaze estimation pipeline including face detection, facial landmark detection, and gaze estimation, running in real time on Raspberry Pi 4, Qualcomm GPU, and Intel CPU.

Publications
Steering LLM Thinking with Budget Guidance
Junyan Li, Wenshuo Zhao, Yang Zhang, Chuang Gan
ACL 2026 Findings
GitHub
CommVQ: Commutative Vector Quantization for KV Cache Compression
Junyan Li, Yang Zhang, Muhammad Yusuf Hassan, Talha Chafekar, Tianle Cai, Zhile Ren, Pengsheng Guo, Foroozan Karimzadeh, Colorado Reed, Chong Wang, Chuang Gan
ICML 2025
GitHub
TesserAct: Learning 4D Embodied World Models
Haoyu Zhen, Qiao Sun, Hongxin Zhang, Junyan Li, Siyuan Zhou, Yilun Du, Chuang Gan
ICCV 2025
Project Page | GitHub
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences
Hongyan Zhi*, Peihao Chen*, Junyan Li*, Shuailei Ma, Xinyu Sun, Tianhang Xiang, Yinjie Lei, Mingkui Tan, Chuang Gan
CVPR 2025
GitHub
FlexAttention for Efficient High-Resolution Vision-Language Models
Junyan Li, Delin Chen, Tianle Cai, Peihao Chen, Yining Hong, Zhenfang Chen, Yikang Shen, Chuang Gan
ECCV 2024
GitHub | Project Page
MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
Yining Hong, Zishuo Zheng, Peihao Chen, Yian Wang, Junyan Li, Chuang Gan
CVPR 2024
GitHub
CoVLM: Composing Visual Entities and Relationships in Large Language Models via Communicative Decoding
Junyan Li, Delin Chen, Yining Hong, Zhenfang Chen, Peihao Chen, Yikang Shen, Chuang Gan
ICLR 2024
GitHub | Project Page
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Junyan Li, Li Lyna Zhang, Jiahang Xu, Yujing Wang, Shaoguang Yan, Yunqing Xia, Yuqing Yang, Ting Cao, Hao Sun, Weiwei Deng, Qi Zhang, Mao Yang
KDD 2023
GitHub | Poster
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction
Han Cai, Junyan Li, Muyan Hu, Chuang Gan, Song Han
ICCV 2023
GitHub | Poster

Honors and Awards

  • [2022.11] Zhejiang Provincial Scholarship
  • [2022.11] Zhejiang University Second Scholarship
  • [2020.11] Zhejiang University Second Scholarship

Education

  • [2023.09 - now] PhD, computer science, University of Massachusetts Amherst.
  • [2019.09 - 2023.06] Undergraduate, computer engineering, University of Illinois Urbana-Champaign.
  • [2019.09 - 2023.06] Undergraduate, computer engineering, Zhejiang University.

Internships

Template inspired by Hongxin Zhang.