Showing 2026Show all
2 papers · 1 filter
cs.LG2026
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-…
cs.CL2026
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…