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

Song Chen

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Vision×2Info Retrieval×1AI×1Crypto×1

Frequent co-authors

Yi-Cheng Wang1×
Chu-Song Chen1×
Yuyang Zhao1×
Yicheng Pan1×
Qiyuan He1×
Jincheng Yu1×

Research Timeline

2026
Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models

The paper introduces Rotated Robustness (RoR), a training-free defense that uses orthogonal transformations to prevent catastrophic model collapse in LLMs caused by hardware bit-flip attacks.

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.

Multimodal Graph RAG for Long-range Visually Rich Document Understanding

This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.

Highlighted terms show continued research focus across papers

Papers

cs.IRcs.CVEmpiricalRecentJun 27, 2026

Multimodal Graph RAG for Long-range Visually Rich Document Understanding

Yi-Cheng Wang, Chu-Song Chen

This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.

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.CRRecentMar 17, 2026

Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models

Deng Liu, Song Chen

The paper introduces Rotated Robustness (RoR), a training-free defense that uses orthogonal transformations to prevent catastrophic model collapse in LLMs caused by hardware bit-flip attacks.

View →