Hello world! I'm a third-year undergraduate at the Tsian Excellence in Engineering Program at Tsinghua University. Driven by a passion for reducing human labor through embodied-AI technology, I'm currently conducting research in robotics and AI at the Institute for AI Industry Research (AIR). As a tech enthusiast, I also enjoy creating tech-related videos on Bilibili and Youtube. If you share a similar drive to dream big, please contact me!
Authors: Kairui Ding, Boyuan Chen, Yuchen Su, Huan-ang Gao, Bu Jin, Chonghao Sima, Wuqiang Zhang, Xiaohui Li, Paul Barsch, Hongyang Li, Hao Zhao
Hint-AD explored the paradigm of aligned interpretability in end-to-end autonomous driving (AD) by aligning a multi-modal language model (LLaMA-v2) with intermediate output from AD models. SOTA is achieved on driving explanation, 3D dense captioning, VQA, and command prediction tasks.
Authors: Kairui Ding, Boyuan Chen, Ruihai Wu, Yuyang Li, Zongzheng Zhang, Huan-ang Gao, Siqi Li, Yixin Zhu, Guyue Zhou, Hao Dong, Hao Zhao
PreAfford is a novel pre-grasping planning framework that improves adaptability across diverse environments and object types by utilizing point-level affordance representation and relay training. Validated on the ShapeNet-v2 dataset and real-world experiments, PreAfford offers a robust solution for manipulating ungraspable objects with two-finger grippers.
