Dogyun Park

research intern, Snap Inc.

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

#4306 · Dogyun Park, Taehoon Lee, Minseok Joo, Hyunwoo J. Kim

We propose blockwise flow modeling framework that aim for optimal Pareto-frontier between generation performance (FID) and inference complexity (FLOPs).