Hao-Yu Zeng

Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier

Reciprocal Guidance is introduced, a runtime draft-verify orchestration framework that adapts speculative decoding to varying serving loads and exploits spare compute capacity through verification-overlapped drafting at low concurrency, while dynamically allocating request-specific draft block sizes as the workload bec...