Wenjia Wang

papers

786

total citations

papers (16)

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

ECCV 2024

citations

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

ICCV 2023arXiv

citations

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

CVPR 2024arXiv

citations

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

CVPR 2025arXiv

citations

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

NEURIPS 2022arXiv

citations

Complexity Matters: Rethinking the Latent Space for Generative Modeling

NEURIPS 2023arXiv

citations

Deep Insights into Noisy Pseudo Labeling on Graph Data

NEURIPS 2023arXiv

citations

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

ICML 2024arXiv

citations

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

NEURIPS 2023arXiv

citations

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

ICCV 2025arXiv

citations

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

ICML 2024arXiv

citations

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

ICLR 2025

citations

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

NEURIPS 2025arXiv

citations

Wenjia Wang

papers (16)

Segmenting Transparent Objects in the Wild

Scene Text Image Super-resolution in the wild

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Deep Insights into Noisy Pseudo Labeling on Graph Data

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

papers (16)

Segmenting Transparent Objects in the Wild

Scene Text Image Super-resolution in the wild

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Deep Insights into Noisy Pseudo Labeling on Graph Data

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling