logo
today local_bar
Image and Video Generation

2 papers across 2 sessions

Poster Session 3

1 paper
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
#4514 · Qinkai XU, yijin liu, YangChen, Lin Yang, Li Li, Yuxiang Fu

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
#4316 · Ruichen Chen, Keith Mills, Liyao Jiang, Chao Gao, Di Niu

We propose a very sparse attention mechanism for diffusion models on T2V and T2I tasks through re-use of softmax statistics.