Qinzhe Hu

Home / Publications

Publications

Qinzhe Hu is shown in bold; * marks equal contribution. Click a figure to enlarge it.

Architecture of Universal Test-Time Training: an expanded uTTT block with a shared fast-weight pool (uTTT-MoE) or a shared dense fast-weight operator (uTTT-Dense) across blocks.

Universal Test-Time Training

Qinzhe Hu*,Zefan Cai*,Ziqiao Ma,Hao Tan,Junjie Hu
* Equal contribution
COLM 2026 Workshop on Efficient Reasoning SpotlightUnder review at NeurIPS 2026

Shares test-time-training fast weights across the whole depth stack instead of keeping one private state per layer, which turns the model into a single recurrence over (chunk, layer) and improves long-context retrieval at equal state size.

Architecture of Universal Test-Time Training: an expanded uTTT block with a shared fast-weight pool (uTTT-MoE) or a shared dense fast-weight operator (uTTT-Dense) across blocks.

OpenReviewCode
Overview of TF-MoE: the mel-band-split Conformer backbone, alternating frequency- and time-wise MoE Conformer blocks, and the sparse MoE feed-forward module with a time/band-wise router.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation

Qinzhe Hu,Chenda Li,Wangyou Zhang,Shujie Liu,Yan Lu,Yanmin Qian
INTERSPEECH 2026 Oral

A sparse Mixture-of-Experts framework that routes experts over time frames and mel bands, raising the capacity of speech-separation models with almost no extra inference cost (+3.8 dB SDR over BSRNN on Libri2Mix at a comparable 4.1 GMACs/s).

Overview of TF-MoE: the mel-band-split Conformer backbone, alternating frequency- and time-wise MoE Conformer blocks, and the sparse MoE feed-forward module with a time/band-wise router.

arXivPDF
Overview of SmartThinker's advantage calculation: trajectory sampling, length-reward calculation from the estimated optimal length, and a dynamic reward coefficient that never penalizes correct trajectories.

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning

Chenzhi Hu,Qinzhe Hu,Yuhang Xu,Junyi Chen,Ruijie Wang,Shengzhong Liu,Jianxin Li,Fan Wu,Guihai Chen
ICML 2026

GRPO-based efficient reasoning with progressive chain-of-thought length calibration: it estimates the optimal reasoning length for each question and adapts the length-reward coefficient, cutting reasoning tokens by up to 52% while improving accuracy on benchmarks such as AIME25.

Overview of SmartThinker's advantage calculation: trajectory sampling, length-reward calculation from the estimated optimal length, and a dynamic reward coefficient that never penalizes correct trajectories.

arXivPDFCodePoster