Zeyu Wang

papers

1,172

total citations

papers (22)

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

CVPR 2020arXiv

413

citations

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

CVPR 2024arXiv

174

citations

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

ICCV 2023arXiv

citations

Towards Unique and Informative Captioning of Images

ECCV 2020arXiv

citations

Revisiting Adversarial Training at Scale

CVPR 2024arXiv

citations

Multi-Query Video Retrieval

ECCV 2022arXiv

citations

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

CVPR 2024arXiv

citations

Rejuvenating image-GPT as Strong Visual Representation Learners

ICML 2024arXiv

citations

RemDet: Rethinking Efficient Model Design for UAV Object Detection

AAAI 2025arXiv

citations

MemoNav: Working Memory Model for Visual Navigation

CVPR 2024arXiv

citations

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

AAAI 2025arXiv

citations

MagicColor: Multi-instance Sketch Colorization

ICCV 2025

citations

Spiking Point Transformer for Point Cloud Classification

AAAI 2025arXiv

citations

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

ICCV 2025arXiv

citations

Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting

ICCV 2025arXiv

citations

Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion

ICCV 2025

citations

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba

ICCV 2025arXiv

citations

Zeyu Wang

papers (22)

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model

An Inverse Scaling Law for CLIP Training

DiT4Edit: Diffusion Transformer for Image Editing

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

Masked Autoencoders Enable Efficient Knowledge Distillers

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

Towards Unique and Informative Captioning of Images

Revisiting Adversarial Training at Scale

Multi-Query Video Retrieval

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

Rejuvenating image-GPT as Strong Visual Representation Learners

RemDet: Rethinking Efficient Model Design for UAV Object Detection

MemoNav: Working Memory Model for Visual Navigation

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

MagicColor: Multi-instance Sketch Colorization

Spiking Point Transformer for Point Cloud Classification

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting

Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba

papers (22)

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model

An Inverse Scaling Law for CLIP Training

DiT4Edit: Diffusion Transformer for Image Editing

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

Masked Autoencoders Enable Efficient Knowledge Distillers

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

Towards Unique and Informative Captioning of Images

Revisiting Adversarial Training at Scale

Multi-Query Video Retrieval

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

Rejuvenating image-GPT as Strong Visual Representation Learners

RemDet: Rethinking Efficient Model Design for UAV Object Detection

MemoNav: Working Memory Model for Visual Navigation

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

MagicColor: Multi-instance Sketch Colorization

Spiking Point Transformer for Point Cloud Classification

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting

Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba