Skip to content

Author

Wei-Fan Jiang

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.

Preprint Oct 2026

Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding

In speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribution. D-PACE (Wu et al., 2026) trains such drafters with a loss that weights each position by its contribution to the expected accepted length. Both i...

Tian-Yu Wu, Zhuo-Hang Wang, Jonathan Geuter et al. · 2 citations
#machine learning Preprint Sep 2026

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

H-Spec is a hybrid Mamba-attention parallel drafter that consumes the two target-context sources through complementary modules, and consistently achieves higher throughput while maintaining lower KV cache utilization than baselines across evaluated concurrency levels.

Wei-Fan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.