Inference-time scaling for diffusion models by pruning bad seeds
ducha_aiki · x · 2026-09-12
A shared approach applies inference-time scaling to diffusion models by pruning "bad seeds" — random seeds that yield low-quality generations — to improve output quality, echoing test-time compute scaling ideas from LLMs but operating at the seed level.
More from Research
- 24 Fields Medalists Sign Protest Letter to OpenAI as Mathematicians Fear Talent Pipeline Collapse — ducha_aiki · 2026-09-12
- sqlite-sparse runs learned sparse retrieval inside SQLite with no model at query time — Much-Ingenuity5415 · 2026-09-12
- Lost in the Middle: LLMs Miss Facts Buried in Long Contexts, Study Shows — thisdudelikesAI · 2026-09-12
- GPT-3 to Chinchilla: A Thread Walking Through the Papers That Reshaped AI — thisdudelikesAI · 2026-09-12
- Kaplan's 2020 Scaling Laws: The Paper Behind Every 'Just Make It Bigger' Decision — thisdudelikesAI · 2026-09-12
- LiFlow: Lidar Point Cloud Completion Method Accepted to ECCV 2026 — ducha_aiki · 2026-09-12