arXiv subjects

Huapeng Zhou

Publications and source records attributed to Huapeng Zhou.

4 recordsLinked to original sources

arXiv2026

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

Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweight module attached to the target rather than a separate model. Applying this design to Automatic Speech Recognition (ASR) introduces an extra problem. The draft can read the whole audio at every step, yet its proposals get worse as it runs on its own. Access is not localization. The accepted text keeps the transcript position explicit, but the draft must also track the changing audio position. In the primary matched comparison, per-step audio access changes the first proposal modestly but roughly doubles later-proposal acceptance. Fixed-width windows show that the audio position explains part of this gap. A correctly placed window recovers continuation, while an equally narrow window at the wrong position reduces it. Late-draft median error reaches 21 frames in the hardest reported condition, while target attention during verification stays within a 2-frame median. We test two ways to reduce this drift. The first reads the audio position from verification attention and uses it to guide the next draft round. It saves time only when the extra accepted tokens offset the readout cost. The second is AnchorDraft, which teaches the draft to track the audio position during training without changing the inference graph. The trained draft improves end-to-end speed at both tested target scales. These results show that ASR self-speculation depends on token prediction, audio-position tracking, and draft cost.

cs.SD↗

arXiv2025

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances video temporal understanding. TEMPURA first applies masked event prediction reasoning to reconstruct missing events and generate step-by-step causal explanations from dense event annotations, drawing inspiration from effective infilling techniques. TEMPURA then learns to perform video segmentation and dense captioning to decompose videos into non-overlapping events with detailed, timestamp-aligned descriptions. We train TEMPURA on VER, a large-scale dataset curated by us that comprises 1M training instances and 500K videos with temporally aligned event descriptions and structured reasoning steps. Experiments on temporal grounding and highlight detection benchmarks demonstrate that TEMPURA outperforms strong baseline models, confirming that integrating causal reasoning with fine-grained temporal segmentation leads to improved video understanding.

cs.CV↗

arXiv2024

First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge

In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard.

cs.CV↗

arXiv2024

Rhyme-aware Chinese lyric generator based on GPT

Neural language representation models such as GPT, pre-trained on large-scale corpora, can effectively capture rich semantic patterns from plain text and be fine-tuned to consistently improve natural language generation performance. However, existing pre-trained language models used to generate lyrics rarely consider rhyme information, which is crucial in lyrics. Using a pre-trained model directly results in poor performance. To enhance the rhyming quality of generated lyrics, we incorporate integrated rhyme information into our model, thereby improving lyric generation performance.

cs.CL↗