Li Wang

papers

466

total citations

papers (17)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

ICML 2024arXiv

citations

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

ICCV 2025arXiv

citations

Dual Super-Resolution Learning for Semantic Segmentation

CVPR 2020

citations

A Spatial RNN Codec for End-to-End Image Compression

CVPR 2020

citations

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

NEURIPS 2025arXiv

citations

Weighted Mutual Learning with Diversity-Driven Model Compression

NEURIPS 2022

citations

Federated Self-Explaining GNNs with Anti-shortcut Augmentations

ICML 2024

citations

HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies

NEURIPS 2022

citations

CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network

ICCV 2023

citations

Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan

ICCV 2023

citations

DARE: Disentanglement-Augmented Rationale Extraction

NEURIPS 2022

citations

Li Wang

papers (17)

Depth-Conditioned Dynamic Message Propagation for Monocular 3D Object Detection

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

Progressive Coordinate Transforms for Monocular 3D Object Detection

NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Dual Super-Resolution Learning for Semantic Segmentation

A Spatial RNN Codec for End-to-End Image Compression

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

Weighted Mutual Learning with Diversity-Driven Model Compression

Federated Self-Explaining GNNs with Anti-shortcut Augmentations

HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies

CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network

Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan

DARE: Disentanglement-Augmented Rationale Extraction

papers (17)

Depth-Conditioned Dynamic Message Propagation for Monocular 3D Object Detection

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

Progressive Coordinate Transforms for Monocular 3D Object Detection

NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Dual Super-Resolution Learning for Semantic Segmentation

A Spatial RNN Codec for End-to-End Image Compression

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

Weighted Mutual Learning with Diversity-Driven Model Compression

Federated Self-Explaining GNNs with Anti-shortcut Augmentations

HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies

CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network

Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan

DARE: Disentanglement-Augmented Rationale Extraction