Chen Wei

18

Papers

104

Total Citations

Papers (18)

Digital Life Project: Autonomous 3D Characters with Social Intelligence

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

De-Diffusion Makes Text a Strong Cross-Modal Interface

Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models

NeurIPS 2025arXiv

Towards Generalizable Tumor Synthesis

Iterative Reorganization With Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Masked Autoencoders Enable Efficient Knowledge Distillers

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

Diffusion Models as Masked Autoencoders

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training

In Defense of Image Pre-training for Spatiotemporal Recognition

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation

CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation

DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation

Growing a Twig to Accelerate Large Vision-Language Models