1 citations · 1 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
BV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding
Suyoung Kim, Jahyun Koo, Hyeonjin Kim +5
Diffusion drafters accelerate speculative decoding by proposing multiple tokens in parallel. Despite recent advances in speculative decoding through sequence-level drafting and ver…
cs.LG2026
Carryover Drafting: Recycling Rejected States for Speculative Decoding
Jahyun Koo, Sunghyeon Woo, Jaeeun Kil +4
Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, ve…