Enxin Song
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark
arXiv 2025
VideoNSA: Native Sparse Attention Scales Video Understanding
arXiv 2025
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
arXiv 2024
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
CVPR 2024 1
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers