Dilin Wang

papers

1,007

total citations

papers (15)

AlphaMatch: Improving Consistency for Semi-Supervised Learning With Alpha-Divergence

CVPR 2021arXiv

citations

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

CVPR 2024arXiv

citations

AutoPartGen: Autoregressive 3D Part Generation and Discovery

NEURIPS 2025

citations

3D Mesh Editing using Masked LRMs

ICCV 2025arXiv

citations

Steepest Descent Density Control for Compact 3D Gaussian Splatting

CVPR 2025arXiv

citations

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

CVPR 2025arXiv

citations

UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping

CVPR 2025arXiv

citations

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

NEURIPS 2025arXiv

citations

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

ICML 2024

citations

Dilin Wang

papers (15)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation

KeepAugment: A Simple Information-Preserving Data Augmentation Approach

AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Fast Point Cloud Generation With Straight Flows

AlphaMatch: Improving Consistency for Semi-Supervised Learning With Alpha-Divergence

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

AutoPartGen: Autoregressive 3D Part Generation and Discovery

3D Mesh Editing using Masked LRMs

Steepest Descent Density Control for Compact 3D Gaussian Splatting

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

papers (15)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation

KeepAugment: A Simple Information-Preserving Data Augmentation Approach

AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Fast Point Cloud Generation With Straight Flows

AlphaMatch: Improving Consistency for Semi-Supervised Learning With Alpha-Divergence

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

AutoPartGen: Autoregressive 3D Part Generation and Discovery

3D Mesh Editing using Masked LRMs

Steepest Descent Density Control for Compact 3D Gaussian Splatting

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once