Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Song Han

Song Han

6 indexed papers

Recent (6 mo)
6
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

Vision×5AI×4Robotics×1ML×1

Frequent co-authors

Wei Huang3×
Shuai Yang3×
Qixin Hu3×
Yukang Chen3×
Yuyang Zhao2×
Yicheng Pan2×

Research Timeline

2026
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training and hardware co-design.

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training and hardware co-design.

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searchable memory.

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searchable memory.

LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization

The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.

Long-WAM: Scaling the Context of World-Action Models

The paper presents Long-WAM, a model-system framework for real-time robot control that scales the context of causal world-action models under real-time control constraints.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIcs.CVEmpiricalRecentOct 7, 2026

Long-WAM: Scaling the Context of World-Action Models

Wei Huang, Bohan Zhang, Chenzhi Liu, Isabella Liu +12 more

The paper presents Long-WAM, a model-system framework for real-time robot control that scales the context of causal world-action models under real-time control constraints.

View →
cs.LGcs.AIEmpirical
Recent
Sep 29, 2026

LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization

Yi Pan, Haocheng Xi, Kan Zhu, Xingyang Li +9 more

The paper proposes LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization for LLMs.

View →
cs.CVRecentJun 1, 2026

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

Qixin Hu, Shuai Yang, Wei Huang, Song Han +1 more

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

View →
cs.CVRecentJun 1, 2026

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation

Qixin Hu, Shuai Yang, Wei Huang, Song Han +1 more

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

View →
cs.CVcs.AIRecentMay 28, 2026

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

Yuyang Zhao, Yicheng Pan, Qiyuan He, Jincheng Yu +5 more

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…

View →
cs.CVcs.AIRecentMay 28, 2026

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

Yuyang Zhao, Yicheng Pan, Qiyuan He, Jincheng Yu +5 more

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…

View →