Mz Dai

2 accepted papers

2026

Test-time Prompt Intervention

Chenxu Yang, Qingyi Si, Mz Dai, Dingyu Yao, Mingyu Zheng, Minghui Chen +2

AAAI 2026technical

Test-time compute has led to remarkable success in the large language model (LLM) community, particularly for complex tasks, where longer chains of thought (CoTs) are generated to enhance reasoning capabilities. However, growing evidence reveals that such reasoning models often produce CoTs plagued

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Mz Dai, Chenxu Yang, Qingyi Si

NeurIPS 2025poster

As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning capabilities to approach Deepseek R1-like reasoning models. However,…

Cited by 0 Source ↗Scholar ↗