4 papers
Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
Shunkai Zhou, Zike Yan, Fei Xue +3
We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving inconsistency issues. Specif…
Reflection-Based Task Adaptation for Self-Improving VLA
Baicheng Li, Dong Wu, Zike Yan +4
Pre-trained Vision-Language-Action (VLA) models represent a major leap towards general-purpose robots, yet efficiently adapting them to novel, specific tasks in-situ remains a sign…
Proactive Scene Decomposition and Reconstruction
Baicheng Li, Zike Yan, Dong Wu +1
Human behaviors are the major causes of scene dynamics and inherently contain rich cues regarding the dynamics. This paper formalizes a new task of proactive scene decomposition an…
Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM
Baicheng Li, Zike Yan, Dong Wu +2
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative par…