Jiajun Liang
23 papers · 2017–2026 · 6 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 ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (40) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Gold 🐣 Hot Topic Early Bird
🧬
Topic Evolution
👥
Mega-Team · Squad
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
🗃️
Keyword Collector
(100)
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(11)
Computer Vision
(10)
Analysis
(7)
Application Areas
(7)
Learning Types · Deep Learning
(6)
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Architectures
(4)
Core Methods
(3)
Models
(3)
Core AI · Computer Vision
(2)
Generation
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory
(2)
Keywords
knowledge distillation
(4)
multimodal learning
(3)
model compression
(3)
neural network
(3)
image classification
(2)
convolutional neural network
(2)
vision transformer
(2)
neural network optimization
(2)
image segmentation
(1)
domain generalization
(1)
semantic segmentation
(1)
binary classification
(1)
image restoration
(1)
entropy minimization
(1)
image generation
(1)
feature learning
(1)
reinforcement learning
(1)
attention mechanism
(1)
video generation
(1)
object detection
(1)
Papers
FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
CVPR 2026
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
CVPR 2026
Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and Divergence
ICML 2025
MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer
AAAI 2025
A Simple Baseline for Efficient Hand Mesh Reconstruction
CVPR 2024
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
ECCV 2024
Cascade Prompt Learning for Visual-Language Model Adaptation
ECCV 2024
HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models
ECCV 2024
Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
ECCV 2024
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
CVPR 2023
Cumulative Spatial Knowledge Distillation for Vision Transformers
ICCV 2023
DOT: A Distillation-Oriented Trainer
ICCV 2023
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
CVPR 2023
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
CVPR 2023
DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior
AAAI 2022
Decoupled Knowledge Distillation
CVPR 2022
Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
ECCV 2022
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
CVPR 2022
Efficient One Pass Self-Distillation with Zipf’s Label Smoothing
ECCV 2022
Explaining Deepfake Detection by Analysing Image Matching
ECCV 2022
Sharp Impossibility Results for Hyper-graph Testing
NeurIPS 2021
Scene Text Recognition from Two-Dimensional Perspective
AAAI 2019
EAST: An Efficient and Accurate Scene Text Detector
CVPR 2017