Showing 2026Show all
3 papers · 1 filter
cs.CV2026
In-Distribution Forcing for Long Video Generation at Test Time
Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo +5
Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to drifting, where colors and textures…
cs.CV2026
Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
Sangwoo Jo, Donggeun Ko, Jayeon Kang +3
Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for p…
cs.LG2026
Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
Sangwoo Jo, Sungjoon Choi
Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs. While prior w…