4 papers · 1 filter
Rethinking FID Through the Geometry of the Reference Dataset
Yunghee Lee, Byeonghyun Pak
Fréchet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We show that this mismatch depends…
Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
Byeongju Woo, Zilin Wang, Byeonghyun Pak +2
Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidenc…
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition
Seokmin Lee, Yunghee Lee, Byeonghyun Pak +1
For robotic agents operating in dynamic environments, learning visual state representations from streaming video observations is essential for sequential decision making. Recent se…
Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
Yunghee Lee, Byeonghyun Pak, Junwha Hong +1
In this paper, we propose Tortoise and Hare Guidance (THG), a training-free strategy that accelerates diffusion sampling while maintaining high-fidelity generation. We demonstrate…