Get started
Author

Fengyuan Shi

Observed names: FengYuan Shi, Shi, FengYuan, Shi, Fengyuan
Institution: Peking University
ORCID: 0000-0003-3239-9389
Observed ORCID: 0000-0003-3239-9389
OpenAlex ID: A5101791514
Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
2023 · Fengyuan Shi, Ruopeng Gao, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 62
PDF
End-to-end dense video grounding via parallel regression
2024 · Fengyuan Shi, Weilin Huang, et al. · Computer Vision and Image Understanding · 15
PDF
BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models
2024 · Fengyuan Shi, Jiaxi Gu, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 12
PDF
Scalable Image Tokenization with Index Backpropagation Quantization
2025 · Fengyuan Shi, Zhuoyan Luo, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 7
PDF
MiMo-Audio: Audio Language Models are Few-Shot Learners
2025 · Core Team, Zhang, Dong, et al. · arXiv (Cornell University) · 2
PDF
MiMo-V2-Flash Technical Report
2026 · Core Team, Xiao, Bangjun, et al. · arXiv (Cornell University) · 1
PDF
Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
2026 · Hao Yu, Hui Li, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
2026 · Yu, Hao, Li, Hui, et al. · arXiv (Cornell University)
PDF
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
2024 · Luo, Zhuoyan, Shi, Fengyuan, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count: 99
H-index: 4
I10-index: 3
Year
Topic
Type