Hengjia Li
9 papers · 2024–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (20) π Conference Polyglot (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15)
π
Keyword Champion
(3)
β‘
Prolific Year
(5)
Conferences
ICCV (3)
AAAI (2)
ICLR (2)
CVPR (1)
WACV (1)
Top co-authors
Keywords
video customization
(3)
video generation
(3)
identity preservation
(2)
reward modeling
(2)
attention mechanism
(2)
unsupervised domain adaptation
(1)
image synthesis
(1)
point cloud
(1)
autonomous driving
(1)
multi-label classification
(1)
domain adaptation
(1)
multimodal learning
(1)
3d object detection
(1)
pseudo labeling
(1)
reward learning
(1)
preference optimization
(1)
diffusion model
(1)
image-text pair
(1)
low-rank adaptation
(1)
image generation
(1)
Papers
RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
WACV 2026
Local Conditional Controlling for Text-to-Image Diffusion Models
AAAI 2025
DreamRelation: Relation-Centric Video Customization
ICCV 2025
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
ICCV 2025
PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
ICCV 2025
SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
ICLR 2025
Few-shot Hybrid Domain Adaptation of Image Generator
ICLR 2024
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training
AAAI 2024
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
CVPR 2024