6 papers
Noise-Space Reward Alignment for Few-Step Generative Models
Woocheol Shin, Taeyoung Yun, Jiwon Sung +7
Few-step generative models produce high-quality samples in one or a few evaluations. However, steering them toward desired properties remains difficult, especially when only black-…
Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding
Dohyun Kim, Sungjun Han, Hyungguk Kim +4
Autoregressive OCR vision-language models accurately convert document images into text and structured markup, but require one sequential decoding step per output token, limiting in…
Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
Dohyun Kim, Seungwoo Lyu, Seung Wook Kim +1
Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and m…
Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos
Youngseo Kim, Dohyun Kim, Geonhee Han +1
Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond…
Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
Dohyun Kim, Sehwan Park, Geonhee Han +2
Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation…
Learning from Convolution-based Unlearnable Datasets
Dohyun Kim, Pedro Sandoval-Segura
The construction of large datasets for deep learning has raised concerns regarding unauthorized use of online data, leading to increased interest in protecting data from third-part…