, a sunset sky) to spread across experts, causing spatiotemporal fragmentation.
Splitting experts by role improves video diffusion model scaling
The authors demonstrate that SplitMoE, which separates experts into semantic and generic branches, outperforms standard MoE in convergence speed, routing coherence, and video generation quality under matched activated-parameter budgets.
Chinese Tech
Yu Xu · Yuxin Zhang · Xiao Yang · Haotian Yang · Yizhi Wang · Xinwei Huang · +4 more
University of Chinese Academy of Sciences · ByteDance · Canva Research · University of Science and Technology Beijing
Research Digest··3 min read
The authors propose SplitMoE, a video diffusion architecture that bifurcates the expert pool into semantic experts (for high-level abstraction) and generic experts (for residual visual details).
Why this paper
From Canva Research and 3 others
In one line
SplitMoE improves video diffusion by separating experts into semantic and generic groups to avoid spatiotemporal fragmentation.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§