★ Highlighted Publications
★ Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
CVPR 2020
★ NAT: Neural Architecture Transformer for Accurate and Compact Architectures
NeurIPS 2019
★ Towards Lightweight Super-Resolution with Dual Regression Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
★ Towards Accurate and Compact Architectures via Neural Architecture Transformer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
Preprints and Additional Publications
VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement
arXiv preprint
RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
arXiv preprint
Asymmetric VAE for One-Step Video Super-Resolution Acceleration
arXiv preprint
QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
arXiv preprint
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
arXiv preprint
Low-bit Model Quantization for Deep Neural Networks: A Survey
arXiv preprint
Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
arXiv preprint
FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training
AAAI 2026
QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution
AAAI 2026
SODiff: Semantic-Oriented Diffusion Model for JPEG Compression Artifacts Removal
AAAI 2026
CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects
TMM 2026
Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
ICLR 2026
Grounding-IQA: Multimodal language grounding model for image quality assessment
ICLR 2026
Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
TIP 2026
Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution
TIP 2026
Effective Diffusion Transformer Architecture for Image Super-Resolution
AAAI 2025
Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-Resolution
AAAI 2025
Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher
ICLR 2025
DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model
IEEE Robotics and Automation Letters, 2025
Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator
NeurIPS 2025
DOVE: Efficient One-step Diffusion Model for Real-world Video Super-Resolution
NeurIPS 2025
PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
NeurIPS 2025
OSCAR: One-step Diffusion Codec across Multiple Bit-rates
NeurIPS 2025
PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
NeurIPS 2025
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
ICCV 2025
Turbo2k: Towards Ultra-efficient and High-quality 2K Video Synthesis
ICCV 2025
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
ICML 2025
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
ICML 2025
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
CVPR 2025
Temporal Action Detection Model Compression by Progressive Block Drop
CVPR 2025
Segment Any-quality Images with Generative Latent Space Enhancement
CVPR 2025
UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
NeurIPS 2024
Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
CVPR 2024
Code: An Explicit Content Decoupling Framework for Image Restoration
CVPR 2024
Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation
IEEE Transactions on Image Processing (TIP), 2024
Binarized Diffusion Model for Image Super-Resolution
NeurIPS 2024
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
NeurIPS 2024
Automated dominative subspace mining for efficient neural architecture search
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024
Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions
CVPR 2023
Improving Fine-tuning of Self-supervised Models with Contrastive Initialization
Neural Networks, 2023
Pareto-aware Neural Architecture Generation for Diverse Computational Budgets
CVPR 2023 Workshop
Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images
ICCV 2023
Boosting Semi-Supervised Learning with Contrastive Complementary Labeling
Neural Networks, 2023
Improving Robustness by Enhancing Weak Subnets
ECCV 2022
Discrimination-aware Network Pruning for Deep Model Compression
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
Conditional Automated Channel Pruning for Deep Neural Networks
IEEE Signal Processing Letters (SPL), 2021
Deep View Synthesis via Self-Consistent Generative Network
IEEE Transactions on Multimedia (TMM), 2021
Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
IEEE Transactions on Multimedia (TMM), 2021
Contrastive Neural Architecture Search with Neural Architecture Comparators
CVPR 2021
AdaXpert: Adapting Neural Architecture for Growing Data
ICML 2021
Disturbance-immune Weight Sharing for Neural Architecture Search
Neural Networks, 2021
Content-Aware Convolutional Neural Networks
Neural Networks, 2021
Improving Generative Adversarial Networks with Local Coordinate Coding
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020
Hierarchical Neural Architecture Search for Single Image Super-Resolution
IEEE Signal Processing Letters (SPL), 2020
Dynamic Extension Nets for Few-shot Semantic Segmentation
ACM MM 2020
Multi-way Backpropagation for Training Compact Deep Neural Networks
Neural Networks, 2020
Discrimination-aware Channel Pruning for Deep Neural Networks
NeurIPS 2018
Adversarial Learning with Local Coordinate Coding
ICML 2018
Double Forward Propagation for Memorized Batch Normalization
AAAI 2018
