activity
20242026
collaborators

7 papers

cs.LG2026

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…

cs.LG2026

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…

cs.CV2026

Token Warping Helps MLLMs Look from Nearby Viewpoints

Phillip Y. Lee, Chanho Park, Mingue Park +3

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual rea…

cs.AI2026

DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving

Seungwoo Yoo, Juil Koo, Daehyeon Choi +1

We propose DiffusionRollout, a novel selective rollout planning strategy for autoregressive diffusion models, aimed at mitigating error accumulation in long-horizon predictions of…

cs.CV2025

Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation

Jaeyeong Kim, Seungwoo Yoo, Minhyuk Sung

We introduce SpLap, a proxy-free deformation method for Gaussian splats (GS) based on a Laplacian operator computed from our novel surface-aware splat graph. Existing approaches to…

cs.LG2025

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…