Junsong Chen
Scholar

Junsong Chen

Google Scholar ID: p4zxPP8AAAAJ
NVIDIA Research Intern, MMLab@HKU
Generative Model， Large Language Model
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,979
 
H-index
13
 
i10-index
13
 
Publications
18
 
Co-authors
19
list available
Contact
No contact links provided.
Publications
14 items
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
2026
Cited
0
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
2026
Cited
0
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
2026
Cited
0
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
2026
Cited
0
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
2026
Cited
2
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
2025
Cited
0
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
2025
Cited
0
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
2025
Cited
0
Resume (English only)
Co-authors
19 total
Enze Xie
Enze Xie
NVIDIA Research, MMLab@HKU
Ping Luo (羅平)
Ping Luo (羅平)
Associate Professor, The University of Hong Kong; MMLAB@HKU
Zhenguo Li
Zhenguo Li
Huawei Noah's Ark Lab, Columbia, CUHK, PKU
Jincheng YU
Jincheng YU
NVIDIA
Han Cai
Han Cai
NVIDIA
Yue Wu
Yue Wu
HKUST, Tencent
Huchuan Lu, IEEE FELLOW
Huchuan Lu, IEEE FELLOW
dalian university of technology
Zhongdao Wang
Zhongdao Wang
Noah's Ark Lab, Huawei