Yujun Cai

5

Papers

43

Total Citations

Papers (5)

6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

LLMs are Good Action Recognizers