FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
Paper
•
2502.05179
•
Published
•
24
ChongjianGE
RhettGee
AI & ML interests
Generative 2D and 3D
Recent Activity
upvoted
a
paper
17 days ago
Rethinking Training Dynamics in Scale-wise Autoregressive Generation
updated
a model
about 2 months ago
Cornucopia/aamm
Organizations
authored
2
papers
11 months ago
authored
4
papers
almost 2 years ago
MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
Paper
•
2304.09801
•
Published
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
Paper
•
2202.07800
•
Published
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
Paper
•
2309.13942
•
Published
•
1
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Paper
•
2403.04692
•
Published
•
40