3 papers
cs.CV2026
FlowFixer: Towards Detail-Preserving Subject-Driven Generation
Jinyoung Jun, Won-Dong Jang, Wenbin Ouyang +2
We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a s…
cs.CV2026
DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency…
cs.LG2025
Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
Samarth Gupta, Raghudeep Gadde, Rui Chen +1
We challenge a fundamental assumption of diffusion models, namely, that a large number of latent-states or time-steps is required for training so that the reverse generative proces…