Huazhe Xu* — accepted AI-conference papers

2024

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Tao Huang*, Guangqi Jiang, Yanjie Ze, Huazhe Xu*

ECCV 2024poster

"Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks. In this work, we propose , a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex vis…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2024

Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation

Yuanchen Ju, Kaizhe Hu, Guowei Zhang, Gu Zhang, Mingrun Jiang, Huazhe Xu*

ECCV 2024poster

"Enabling robotic manipulation that generalizes to out-of-distribution scenes is a crucial step toward the open-world embodied intelligence. For human beings, this ability is rooted in the understanding of semantic correspondence among different objects, which helps to naturally transfer the interac…

Cited by 48 Source ↗PDF ↗Scholar ↗