I am a 1st-year Ph.D. student at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Jun Zhang. I received my B.E. degree from Beihang University. I also work as a research intern at SenseTime Research, closely with Dr. Ruihao Gong. Previously, I have interned at Microsoft Research Asia and SenseTime Research. My research interest focuses on efficient vision and language generative models.

🔥 News

  • 2025.06:  🎉🎉 Our Temporal Feature Matters is accepted to TPAMI.
  • 2025.05:  🎉🎉 Our HarmoniCa is accepted to ICML.
  • 2024.10:  🎉🎉 Our LLMC is accepted to EMNLP Industry Track.
  • 2024.07:  🎉🎉 Our PTSBench is accepted to ACM MM.
  • 2024.02:  🎉🎉 Our TFMQ-DM is accepted to CVPR as a Highlight Poster (Top $2.8\%$).

📝 Publications

(* indicates equal contribution, 📧 indicates corresponding author.)

Preprint
sym

QVGen: Pushing the Limit of Quantized Video Generative Models

Yushi Huang, Ruihao Gong📧, Jing Liu, Yifu Ding, Chengtao Lv, Haotong Qin, Jun Zhang📧

[paper] [abstract]
ICML 2025
sym

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration sym

Yushi Huang*, Zining Wang*, Ruihao Gong📧, Jing Liu, Xinjie Zhang, Jinyang Guo, Xianglong Liu, Jun Zhang📧

[paper] [code] [abstract]
TPAMI 2025
sym

Temporal Feature Matters: A Framework for Diffusion Model Quantization sym

Yushi Huang, Ruihao Gong, Xianglong Liu📧, Jing Liu, Yuhang Li, Jiwen Lu, Dacheng Tao

[paper] [code] [abstract]
EMNLP 2024 Industry Track
sym

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit sym

Ruihao Gong*, Yang Yong*, Shiqiao Gu*, Yushi Huang*, Chengtao Lv, Yunchen Zhang, Dacheng Tao, Xianglong Liu📧

[paper] [code] [abstract]
ACM MM 2024
sym

PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models sym

Zining Wang, Jinyang Guo, Ruihao Gong, Yang Yong, Aishan Liu, Yushi Huang, Jiaheng Liu, Xianglong Liu📧

[paper] [code] [abstract]
CVPR 2024 Highlight
sym

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models sym

Yushi Huang*, Ruihao Gong*, Jing Liu, Tianlong Chen, Xianglong Liu📧

[paper] [code] [abstract] [project page]

📋 Services

  • Conference Reviews: NeurIPS, ICLR, ICML, COLM.

📖 Educations

  • 2025.02 - Now, Ph.D. in Electronic Computer and Engineering, the Hong Kong University of Science and Technology.
  • 2020.09 - 2024.06, B.Eng. in Computer Science and Engineering, Shenyuan Honors College, Beihang University.

💻 Internships

  • 2025.02 - Now, SenseTime Research.
  • 2024.12 - 2025.02, Microsoft Research Asia.
  • 2023.05 - 2024.12, SenseTime Research.