7 papers
Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation
Junming Zhang, Shuyu Yin, Peilin Liu +2
Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TTA methods rely on backpropag…
Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
Haochen Niu, Kanyu Zhang, Shuyu Yin +3
In real-world robotic manipulation, states typically admit a neighborhood of near-equivalent actions. That is, for each state, there exist a feasible action neighborhood (FAN) rath…
SSMG-Nav: Enhancing Lifelong Object Navigation with Semantic Skeleton Memory Graph
Haochen Niu, Lantao Zhang, Xingwu Ji +3
Navigating to out-of-sight targets from human instructions in unfamiliar environments is a core capability for service robots. Despite substantial progress, most approaches underut…
A Skeleton-Based Topological Planner for Exploration in Complex Unknown Environments
Haochen Niu, Xingwu Ji, Lantao Zhang +3
The capability of autonomous exploration in complex, unknown environments is important in many robotic applications. While recent research on autonomous exploration have achieved m…
Brain-Inspired Online Adaptation for Remote Sensing with Spiking Neural Network
Dexin Duan, Peilin liu, Bingwei Hui +1
On-device computing, or edge computing, is becoming increasingly important for remote sensing, particularly in applications like deep network-based perception on on-orbit satellite…
An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
Xingwu Ji, Haochen Niu, Dexin Duan +3
Recently, learning-based robotic navigation systems have gained extensive research attention and made significant progress. However, the diversity of open-world scenarios poses a m…