Qingyu Yin

Research

Currently focused on scaling RL. Previously worked on alignment.

Education

Zhejiang University
2022.09 — 2026.06
B.A. in English (Linguistics)

Experience

MiniMax · Post-Training Team TOP Talent Intern 人才计划实习生
2026.02 — Present
Post-training of M2.7 and M3 series models.
JD Group, JoyAI · Post-Training Team JD Young Intern
2025.11 — 2026.02
As one of 3 core members, built the entire RL pipeline for JoyAI-LLM-Flash from scratch.
Rednote Hi Lab · Post-Training Team Ace Top Talent Intern 人才计划实习生
2025.07 — 2025.11
Post-training of dots.llm2 / dots.vlm2.

Publications

10 papers published at ICML, ICLR, EMNLP, ACL, etc. — 6 as first author, 2 Oral Presentations.

Evaluating Parameter Efficient Methods for RLVR
ICML’26
Qingyu Yin*, Yulun Wu*, Zhennan Shen*, Sunbowen Li, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu.
Constrain Alignment with Sparse AutoEncoders
ICML’25
Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang.
StableMask: Refining Causal Masking in Decoder-only Transformers
ICML’24
Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao, Jianhua Yao, Xiaoyu Shen, Qiang Zhang.
MiSS: Balancing LoRA Performance and Efficiency with Simple Shard Sharing
ICLR’26
Jiale Kang*, Qingyu Yin*.
ModRWKV: Transformer Multimodality in Linear Time
EMNLP’25 🏆 Oral
Qingyu Yin*, Jiale Kang*, Ziyin Yue*, Jiang Rui, Weile Li, Zening Lu, Zhouran Ji.
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
EMNLP’24 Findings
Qingyu Yin, Xuzheng He, Luoao Deng, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang.
Aligned LLMs’ Safety Mechanisms Tend to Be Anchored in The Template Region
ACL’25 🏆 Oral
Chak Tou Leong, Qingyu Yin, Jian Wang, Wenjie Li.
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
ICML’26
Wenxuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shaosheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen, et al.
Interleaving Reasoning for Better Text-to-Image Generation
ICLR’26
Wenxuan Huang, Shuang Chen, Zheyong Xie, Shaosheng Cao, Shixiang Tang, Yufan Shen, Qingyu Yin, Wenbo Hu, Xiaoman Wang, Yuntian Tang, et al.
MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction LLMs
ACL’26 Findings
Chengguang Gan, Sunbowen Lee, Qingyu Yin, Xinyang He, Hanjun Wei, Yunhao Liang, Younghun Lim, Shijian Wang, Hexiang Huang, Qinghao Zhang, et al.