The authors developed data-space iteration, a sampling framework in which a shared generator starts from noise and repeatedly revises its current image prediction.
Direct data-space refinement improves few-step generation without flow schedules
A shared generator repeatedly updates images directly, matching or exceeding schedule-tuned flow methods on class-conditional ImageNet.
Chinese Tech
Shanchuan Lin · Yansong Peng · Fu-Yun Wang · Haoqi Fan
ByteDance Seed
Research Digest··2 min read
Lin and colleagues replace the fixed timestep schedules used by conventional few-step flow generators with repeated refinement in image space.
Why this paper
From ByteDance Seed
In one line
Data-space iteration directly refines predictions in data space and outperforms standard flow discretization for few-step generation.
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 (3 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.
§