Junyi Zhang

8

Papers

30

Total Citations

Papers (8)

Pre-training Auto-regressive Robotic Models with 4D Representations

CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World

From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence