Yawei Li

papers

1,397

total citations

papers (18)

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

CVPR 2023arXiv

289

citations

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

CVPR 2020arXiv

208

citations

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

CVPR 2021arXiv

148

citations

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

CVPR 2023arXiv

citations

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

CVPR 2024arXiv

citations

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

CVPR 2021arXiv

citations

Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information

NEURIPS 2021arXiv

citations

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

ICCV 2021arXiv

citations

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

CVPR 2021arXiv

citations

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

ECCV 2024arXiv

citations

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

ICCV 2025arXiv

citations

Semantic and Sequential Alignment for Referring Video Object Segmentation

CVPR 2025

citations

Calibrating LLMs with Information-Theoretic Evidential Deep Learning

ICLR 2025arXiv

citations

MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures

CVPR 2025arXiv

citations

Yawei Li

papers (18)

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

DHP: Differentiable Meta Pruning via HyperNetworks

Revisiting Random Channel Pruning for Neural Network Compression

Reference-Based Image Super-Resolution with Deformable Attention Transformer

MambaIRv2: Attentive State Space Restoration

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

Semantic and Sequential Alignment for Referring Video Object Segmentation

Calibrating LLMs with Information-Theoretic Evidential Deep Learning

MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures

papers (18)

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

DHP: Differentiable Meta Pruning via HyperNetworks

Revisiting Random Channel Pruning for Neural Network Compression

Reference-Based Image Super-Resolution with Deformable Attention Transformer

MambaIRv2: Attentive State Space Restoration

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

Semantic and Sequential Alignment for Referring Video Object Segmentation

Calibrating LLMs with Information-Theoretic Evidential Deep Learning

MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures