Scholar
Fangyi Chen
Google Scholar ID: Wq3W7QcAAAAJ
Research Scientist, ByteDance
Deep Learning
Multimodal LLM
Object Detection
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
783
H-index
10
i10-index
10
Publications
20
Co-authors
15
list available
Contact
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
8 items
Referring Layer Decomposition
2026
Cited
0
Sigmoid-FTRL: Design-Based Adaptive Neyman Allocation for AIPW Estimators
2025
Cited
0
MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
2025
Cited
0
Scalable Scientific Interest Profiling Using Large Language Models
2025
Cited
0
STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
2025
Cited
0
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
2025
Cited
0
Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition
2024
Cited
0
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
arXiv.org · 2024
Cited
3
Resume (English only)
Academic Achievements
[{'Paper': 'RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection', 'Authors': 'Fangyi Chen, Han Zhang, Zhantao Yang, Hao Chen, Kai Hu, Marios Savvides', 'Conference/Journal': 'Preprint'}, {'Paper': 'Enhanced Training of Query-Based Object Detection via Selective Query Recollection', 'Authors': 'Fangyi Chen, Han Zhang, Kai Hu, Yukai Huang, Chenchen Zhu, Marios Savvides', 'Conference/Journal': 'CVPR 2023'}, {'Paper': 'Unitail: Detecting, Reading, and Matching in Retail Scene', 'Authors': 'Fangyi Chen, Han Zhang, Zaiwang Li, Jiachen Dou, Shentong Mo, Hao Chen, Yongxin Zhang, Uzair Ahmed, Chenchen Zhu, Marios Savvides', 'Conference/Journal': 'ECCV 2022'}, {'Patent': 'US12189714B2', 'Title': 'System and method for improved few-shot object detection using a dynamic semantic network'}, {'Patent': 'US20250182450A1', 'Title': 'System and method for weapon detection with pose estimation'}, {'Patent': 'US12266156B2', 'Title': 'System and method for solving missing annotation object detection'}]
Background
Research interests: Deep learning and computer vision, with a focus on multimodal large language model and open-world scene understanding.
Miscellany
Lucky to have opportunities to work with Ker-Jiun Wang, Yutong Zheng, Dipan Pal, Raied Aljadaany, and Chenchen Zhu.
Co-authors
15 total
Marios Savvides
Professor of Electrical and Computer Engineering, Carnegie Mellon University
Chenchen Zhu
Research Scientist, Meta Reality Labs
Han Zhang
Carnegie Mellon University
Uzair Ahmed
Carnegie Mellon University
Co-author 5
Hao Chen
Carnegie Mellon University
Yu-Kai Huang
Carnegie Mellon University
Bhiksha Raj
Carnegie Mellon University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up