Skip to content

Author

Hua-Peng Zhou

3 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 Sep 2026

Whisper-Flash: Acoustically Conditioned Parallel Drafting for Faster Whisper Decoding

This work presents Whisper-Flash, a two-layer drafter built on a property of speech recognition: the words still to be written have already been spoken, which reads Whisper's encoded audio and accepted decoder states and proposes eight tokens in a single forward pass.

Hua-Peng Zhou, Hua-Yu Wang, Junkai Wu et al. · 0 citations
#natural language process... Preprint Aug 2026

TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding

TreeSpark is introduced, which reads a parent-conditioned distribution from the drafter's existing Markov head at negligible cost, calibrates it into an edge-acceptance estimate, and lets path survival govern everything else: best-first expansion, per-round stopping, and a load-adaptive serving policy.

Hua-Peng Zhou, Hua-Yu Wang, Xin-Yu Wang · 2 citations · ⚡1
Preprint Aug 2026

Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost

Results show that ASR self-speculation depends on token prediction, audio-position tracking, and draft cost, and AnchorDraft, which teaches the draft to track the audio position during training without changing the inference graph, improves end-to-end speed at both tested target scales.

Xin-Yu Wang, Hua-Peng Zhou, Zi-Yu Zhao et al. · 1 citation · ⚡1

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