Jingyuan Liu
7 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(21)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Computer Vision
(5)
Deep Learning
(5)
Artificial Intelligence
(3)
Machine Learning
(3)
Analysis
(3)
Generation
(3)
Processing
(3)
Learning Paradigms
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Application Areas
(1)
Core AI
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Types · Machine Learning
(1)
Keywords
diffusion model
(2)
image relighting
(2)
image generation
(1)
minimax optimality
(1)
3d vision
(1)
image synthesis
(1)
computer graphics
(1)
distributed estimation
(1)
image harmonization
(1)
high-dimensional estimation
(1)
human motion synthesis
(1)
distribution shift
(1)
hierarchical framework
(1)
motion generation
(1)
human pose estimation
(1)
scene understanding
(1)
synthetic data
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
action recognition
(1)
Papers
Group Orthogonal Low-Rank Adaptation for RGB-T Tracking
AAAI 2026
High-dimensional Parameter Transfer With Fused-Regularizer
JMLR 2026
TokenLight: Precise Lighting Control in Images using Attribute Tokens
CVPR 2026
Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization
CVPR 2025
SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces
CVPR 2025
Towards Diverse and Natural Scene-Aware 3D Human Motion Synthesis
CVPR 2022
Normalized Human Pose Features for Human Action Video Alignment
ICCV 2021