Author

Youngjin Kwon

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Oct 2026

AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines

Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts. Yet existing methods fall short in agent pipelines: much of the reusable text is missing from their corpora or stored in a form that...

Sumin Lee, Sukmin Cho, Suengjae Lim et al. · 0 citations

#artificial intelligence Jun 2026

WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

This work empirically finds that drafting accuracy fluctuates dramatically within a single sequence, leaving significant performance unrealised by static paradigms and coarse-grained routing, and introduces WhiFlash, the first cross-paradigm SD method that unifies autoregressive and diffusion-based parallel drafting un...

Youngjin Kwon, Miles Williams, Rui Li et al. · arXiv.org · 1 citation