1 citations · 1 across the 8 of their papers we have counts for
9 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…
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…
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…
Explicit Mutual Information Maximization for Self-Supervised Learning
Lele Chang, Peilin Liu, Qinghai Guo +1
Recently, self-supervised learning (SSL) has been extensively studied. Theoretically, mutual information maximization (MIM) is an optimal criterion for SSL, with a strong theoretic…
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…
Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning
Shuyu Yin, Fei Wen, Peilin Liu +1
The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the idea…
Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation
Shuyu Yin, Fei Wen, Peilin Liu +1
Semi-gradient Q-learning is applied in many fields, but due to the absence of an explicit loss function, studying its dynamics and implicit bias in the parameter space is challengi…