Junsong Chen

About Me

I am currently a research intern at NVIDIA Research supervised by Dr. Enze Xie and Prof. Song Han. I am also a Ph.D. student in MMLab at the University of Hong Kong under the supervision of Prof. Ping Luo. Previously, I have received my M.E. degree from IIAU Lab, advised by Prof. Huchuan Lu. My research area is the intersection of AIGC and machine learning, especially algorithm and system co-design for generative AI and its applications.

News

• [5/2025] 💪SANA-1.5(Inference Test Scaling) is accepted to ICML’25.,
• [3/2025] 💪SANA-1.5(Inference Test Scaling) , 🏃SANA-Sprint(One-step Diffusion) are all released.
• [1/2025] ⚡️Sana(Oral) , DCAE , HART are all accepted to ICLR’25.
• [10/2024] “⚡️SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer” is released.
• [10/2024] “DC-AE” and “HART” code & paper are released.
• [06/2024] “PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation” is accepted to ECCV’24.
• [01/2024] “PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis” is accepted as Spotlight paper to ICLR’24.
• [07/2023] “MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation” is accepted to ICCV’23.
• [03/2023] “ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data” is accepted to CVPR’23.

Selected Publications

Experiences

Awards & Honors

Honors

Services

• Conference Reviewer: ICLR, ICML, NeurIPS

Powered by Jekyll and Minimal Light theme.