Author

Miao Peng

Observed name: Peng, Miao

Institutions: Tencent (China), The Hong Kong University of Science and Technology (Guangzhou)

Observed institutions: Tencent (China), The Hong Kong University of Science and Technology (Guangzhou), Zhejiang University

OpenAlex ID: A5144405118

Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping

2026 · Miao Peng, Weizhou Shen, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 1

Scalable Frequency- and Length-Aware Subdocument Deduplication for Large Language Model Pretraining

2026 · Wang, Hai, Wang, Chenhao, et al. · arXiv (Cornell University)

Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training

2026 · Tao, Jiawen, Peng, Miao, et al. · arXiv (Cornell University)

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

2026 · Wang, Yan, Zhang, Qifan, et al. · arXiv (Cornell University)

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

2026 · Wang, Yuyao, Zhang, Zhongjian, et al. · arXiv (Cornell University)

Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping

2026 · Peng, Miao, Shen, Weizhou, et al. · arXiv (Cornell University)

MMOTS: A Multi-UAV Pursuit-Evasion Game Training Strategy Relying on Offline Reinforcement Learning

2025 · Zekai Zhang, Xiangjin Li, et al. · Lecture notes in computer science

Works count: 7

Citation count: 1

H-index: 1

I10-index: