2 papers
cs.CL2026
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with oppo…
cs.CV2024
LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation
Fan Deng, Yaguang Wu, Xinyang Yu +4
Recently, text-to-image models based on diffusion have achieved remarkable success in generating high-quality images. However, the challenge of personalized, controllable generatio…