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

Publications

18 items

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

2026

Cited

0

Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge

2026

Cited

0

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

2026

Cited

0

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

2026

Cited

0

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

Co-authors

18 total

NVIDIA Research, MMLab@HKU

Ping Luo (羅平)

Associate Professor, The University of Hong Kong; MMLAB@HKU

Huawei Noah's Ark Lab, Columbia, CUHK, PKU

Huchuan Lu, IEEE FELLOW

dalian university of technology

Noah's Ark Lab, Huawei