Wei Hu

papers

1,878

total citations

papers (24)

Diffusion Probabilistic Models for 3D Point Cloud Generation

CVPR 2021arXiv

937

citations

Score-Based Point Cloud Denoising

ICCV 2021arXiv

210

citations

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries

CVPR 2021arXiv

167

citations

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

NEURIPS 2022arXiv

citations

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

ECCV 2020arXiv

citations

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

NEURIPS 2020arXiv

citations

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations

CVPR 2020arXiv

citations

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

NEURIPS 2023arXiv

citations

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

ICCV 2023arXiv

citations

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

ICCV 2023arXiv

citations

Neural Capture of Animatable 3D Human from Monocular Video

ECCV 2022arXiv

citations

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning

AAAI 2024arXiv

citations

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

CVPR 2024arXiv

citations

Knowledge Graph Error Detection with Contrastive Confidence Adaption

AAAI 2024arXiv

citations

Controllable Protein Sequence Generation with LLM Preference Optimization

AAAI 2025arXiv

citations

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

NEURIPS 2025arXiv

citations

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

ICCV 2025arXiv

citations

DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation

ICML 2024

citations

Large Scene Generation with Cube-Absorb Discrete Diffusion

ICCV 2025

citations

Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack

AAAI 2024

citations

Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks

CVPR 2025

citations

Wei Hu

papers (24)

Diffusion Probabilistic Models for 3D Point Cloud Generation

Score-Based Point Cloud Denoising

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

Neural Capture of Animatable 3D Human from Monocular Video

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

Knowledge Graph Error Detection with Contrastive Confidence Adaption

Controllable Protein Sequence Generation with LLM Preference Optimization

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation

Large Scene Generation with Cube-Absorb Discrete Diffusion

Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack

Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks

papers (24)

Diffusion Probabilistic Models for 3D Point Cloud Generation

Score-Based Point Cloud Denoising

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

Neural Capture of Animatable 3D Human from Monocular Video

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

Knowledge Graph Error Detection with Contrastive Confidence Adaption

Controllable Protein Sequence Generation with LLM Preference Optimization

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation

Large Scene Generation with Cube-Absorb Discrete Diffusion

Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack

Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks