Pengyuan Lyu

Researcher, Tencent

Joined

July 2019

Names

Pengyuan Lyu (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Researcher

Tencent (tencent.com)

2024 – Present

Researcher

Baidu (baidu.com)

2020 – 2024

Researcher

Tencent YouTu Lab (tencent.com)

2018 – 2020

MS student

Huazhong University of Science and Technology (hust.edu.cn)

2015 – 2018

Advisors, Relations & Conflicts

MS Advisor

Xiang Bai

2015 – 2018

Expertise

VLM

2023 – Present

OCR

2014 – 2023

Publications

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
Zhengyao Fang, Pengyuan Lyu, Chengquan Zhang, Guangming Lu, Jun Yu, Wenjie Pei
- ICLR 2026 Poster
- Readers: Everyone
R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models
linger Deng, Yuliang Liu, Bohan Li, Dongliang Luo, Liang Wu, Chengquan Zhang, Pengyuan Lyu, Ziyang Zhang, Gang Zhang, Errui Ding, Yingying Zhu, Xiang Bai
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Unified Multi-granularity Text Detection with Interactive Attention
Xingyu Wan, Chengquan Zhang, Pengyuan Lyu, Sen Fan, Zihan Ni, Kun Yao, Errui Ding, Jingdong Wang
- ICML 2024 Spotlight
- Readers: Everyone
MaskOCR: Scene Text Recognition with Masked Vision-Language Pre-training
Pengyuan Lyu, Chengquan Zhang, Shanshan Liu, Meina Qiao, Yangliu Xu, Liang Wu, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang
- Accepted by TMLR
- Readers: Everyone
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers
Zengyuan Guo, Yuechen Yu, Pengyuan Lv, Chengquan Zhang, Haojie Li, Zhihui Wang, Kun Yao, Jingtuo Liu, Jingdong Wang
- 2022 (modified: 04 Nov 2022)
- CoRR 2022
- Readers: Everyone
Decoupling Recognition from Detection: Single Shot Self-Reliant Scene Text Spotter
Jingjing Wu, Pengyuan Lyu, Guangming Lu, Chengquan Zhang, Kun Yao, Wenjie Pei
- 2022 (modified: 04 Nov 2022)
- ACM Multimedia 2022
- Readers: Everyone
Decoupling Recognition from Detection: Single Shot Self-Reliant Scene Text Spotter
Jingjing Wu, Pengyuan Lyu, Guangming Lu, Chengquan Zhang, Kun Yao, Wenjie Pei
- 2022 (modified: 04 Nov 2022)
- CoRR 2022
- Readers: Everyone
MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining
Pengyuan Lyu, Chengquan Zhang, Shanshan Liu, Meina Qiao, Yangliu Xu, Liang Wu, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang
- 2022 (modified: 04 Nov 2022)
- CoRR 2022
- Readers: Everyone
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
Pengfei Wang, Chengquan Zhang, Fei Qi, Shanshan Liu, Xiaoqiang Zhang, Pengyuan Lyu, Junyu Han, Jingtuo Liu, Errui Ding, Guangming Shi
- 2021 (modified: 04 Nov 2022)
- CoRR 2021
- Readers: Everyone
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
Pengfei Wang, Chengquan Zhang, Fei Qi, Shanshan Liu, Xiaoqiang Zhang, Pengyuan Lyu, Junyu Han, Jingtuo Liu, Errui Ding, Guangming Shi
- 2021 (modified: 04 Nov 2022)
- AAAI 2021
- Readers: Everyone

View all 31 publications

Co-Authors

View all 63 co-authors