Scholar
Hengjia Li
Google Scholar ID: FstE4t0AAAAJ
Zhejiang University
image generation
video generation
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
180
H-index
8
i10-index
7
Publications
14
Co-authors
22
list available
Contact
GitHub
Open ↗
LinkedIn
Open ↗
Publications
11 items
PhyRPR: Training-Free Physics-Constrained Video Generation
2026
Cited
0
ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing
arXiv.org · 2026
Cited
0
Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition
2025
Cited
0
Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model
2025
Cited
0
RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence
2025
Cited
0
Multi-View Consistent Human Image Customization via In-Context Learning
2025
Cited
0
RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
2025
Cited
0
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
2025
Cited
0
Load more
Resume
Academic Achievements
Jun. 2025: Three papers accepted by ICCV 2025 (two as first author)
Jan. 2025: One paper accepted by ICLR 2025
Dec. 2024: One paper accepted by AAAI 2025
Feb. 2024: One paper accepted by CVPR 2024
Jan. 2024: First-author paper 'FHDA' accepted by ICLR 2024
Dec. 2023: Paper 'TagCLIP' accepted by AAAI 2024
Serving as reviewer for ICCV 2025, ICML 2025, and CVPR 2025
Co-authors
15 total
Boxi Wu
Zhejiang University
Zheng Yang
Fabu
Binbin Lin
University of Michigan
Liang Peng
Zhejiang University
Deng Cai
Professor of Computer Science, Zhejiang University
Yuqi Lin
Zhejiang University
Wei Liu, AAAS/IEEE/IAPR Fellow
Founder and CEO at Video Rebirth
Minghao Chen
Hangzhou Dianzi University