Haoxuan Wang

papers

115

total citations

papers (11)

STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction

CVPR 2025arXiv

citations

CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation

ICCV 2025

citations

Distilling Long-tailed Datasets

CVPR 2025arXiv

citations

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

NEURIPS 2025arXiv

citations

Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration

CVPR 2025

citations

Efficient Multimodal Dataset Distillation via Generative Models

NEURIPS 2025arXiv

citations

X-Field: A Physically Informed Representation for 3D X-ray Reconstruction

NEURIPS 2025

citations

I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting

ICCV 2025

citations

Haoxuan Wang

papers (11)

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction

CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation

Distilling Long-tailed Datasets

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration

Efficient Multimodal Dataset Distillation via Generative Models

X-Field: A Physically Informed Representation for 3D X-ray Reconstruction

I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting

papers (11)

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction

CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation

Distilling Long-tailed Datasets

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration

Efficient Multimodal Dataset Distillation via Generative Models

X-Field: A Physically Informed Representation for 3D X-ray Reconstruction

I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting