1 citations · 1 across the 7 of their papers we have counts for
4 papers · 1 filter
RW-Flow: One-Step Generation on Compact Manifolds via Wasserstein Gradient Flows
Ualibyek Nurgulan, Seungwoo Yoo, Prin Phunyaphibarn +1
Manifold-valued data, and consequently the distributions they induce, are prevalent across many domains, ranging from the locations of geospatial events, such as earthquakes, to bi…
PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
Mingue Park, Jisung Hwang, Seungwoo Yoo +2
We introduce , a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFM…
BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
Yunhong Min, Juil Koo, Seungwoo Yoo +1
We introduce BézierFlow, a lightweight training approach for few-step generation with pretrained diffusion and flow models. BézierFlow achieves a 2-3x performance improvement for s…
Neural Green's Functions
Seungwoo Yoo, Kyeongmin Yeo, Jisung Hwang +1
We introduce Neural Green's Function, a neural solution operator for linear partial differential equations (PDEs) whose differential operators admit eigendecompositions. Inspired b…