Bowen Ping

MS student, Peking University

Joined

February 2024

Names

Bowen Ping (Preferred)

Emails

****@stu.pku.edu.cn (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

MS student

Peking University (stu.pku.edu.cn)

2023 – 2026

Advisors, Relations & Conflicts

Coauthor

Shanghang Zhang

2025 – 2026

PhD Advisor

Baobao Chang

2025 – 2026

Coauthor

Zhiyuan Liu

2023 – 2025

Expertise

Long Context

2024 – 2025

Large Language Models

2023 – 2025

Parameter Efficient Fine-tuning

2023 – 2024

Model Compression

2023 – 2024

Publications

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
Bowen Ping, Zijun Chen, Yiyao Yu, Tingfeng Hui, Junchi Yan, Baobao Chang
- CoRR 2026
- Readers: Everyone
LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information
Bowen Ping
- OpenReview Archive Direct Upload
- Readers: Everyone
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Bowen Ping
- OpenReview Archive Direct Upload
- Readers: Everyone
LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information
Bowen Ping, Jiali Zeng, Fandong Meng, Shuo Wang, Jie Zhou, Shanghang Zhang
- ACL (Findings) 2025
- Readers: Everyone
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Bowen Ping, Shuo Wang, Hanqing Wang, Xu Han, Yuzhuang Xu, Yukun Yan, Yun Chen, Baobao Chang, Zhiyuan Liu, Maosong Sun
- NeurIPS 2024 poster
- Readers: Everyone
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Hanqing Wang, Bowen Ping, Shuo Wang, Xu Han, Yun Chen, Zhiyuan Liu, Maosong Sun
- ACL (1) 2024
- Readers: Everyone
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Bowen Ping, Shuo Wang, Hanqing Wang, Xu Han, Yuzhuang Xu, Yukun Yan, Yun Chen, Baobao Chang, Zhiyuan Liu, Maosong Sun
- NeurIPS 2024
- Readers: Everyone

Bowen Ping

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models

Co-Authors