Junchao Liao
Scholar

Junchao Liao

Google Scholar ID: -nCLQeQAAAAJ
Huazhong University of Science and Technology
computer visionmulti-modal analysisOCR
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
90
 
H-index
2
 
i10-index
2
 
Publications
5
 
Co-authors
4
list available
Contact
GitHubOpen ↗
Publications
6 items
Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
2025
Cited
0
LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing
2025
Cited
0
Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation
2025
Cited
0
TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis
2025
Cited
0
Cross-layer attentive feature upsampling for low-latency semantic segmentation
Machine Vision and Applications · 2024
Cited
1
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
arXiv.org · 2024
Cited
21
Resume (English only)
Co-authors
4 total
Tianheng Cheng
Tianheng Cheng
ByteDance Seed
Hao Wang （王豪）
Hao Wang （王豪）
Huawei
Xiang Bai
Xiang Bai
Huazhong University of Science and Technology (HUST)
Wenyu Liu
Wenyu Liu
Huazhong University of Science and Technology