Yu Sun

21

Papers

116

Total Citations

Papers (21)

One-Minute Video Generation with Test-Time Training

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

PromptHMR: Promptable Human Mesh Recovery

Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales

Putting People in Their Place: Monocular Regression of 3D People in Depth

ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments

Monocular, One-Stage, Regression of Multiple 3D People

Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS

Learning Cross-Video Neural Representations for High-Quality Frame Interpolation

Supervised Word Mover's Distance

Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled Representation

TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

ChatPose: Chatting about 3D Human Pose

High-Order Contrastive Learning with Fine-grained Comparative Levels for Sparse Ordinal Tensor Completion

KDGAN: Knowledge Distillation with Generative Adversarial Networks

Block Coordinate Regularization by Denoising

Test-Time Training with Masked Autoencoders

From Word Embeddings To Document Distances

On Calibration of Modern Neural Networks

Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random