← Search

Mingue Park

2 accepted papers

2026

PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models

ICLR 2026poster

We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of generative models for discrete data, offering strong performance. However, the…

Cited by 0SourcecodeScholar
2026

Token Warping Helps MLLMs Look from Nearby Viewpoints

CVPR 2026

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 reasoning, they remain fragile to viewpoint changes, as pixel-wise warping is highly sensitive to small depth errors and of

Cited by 0SourcecodeScholar