5 papers
UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation
Zhuofan Zhang, Tianxu Wang, Guoxi Zhang +6
Mobile manipulation requires a robot to navigate to a target object or receptacle and then perform intended manipulation. However, reaching the vicinity of the target does not guar…
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +2
In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability t…
MMNavAgent: Multi-Magnification WSI Navigation Agent for Clinically Consistent Whole-Slide Analysis
Zhengyang Xu, Han Li, Jingsong Liu +10
Recent AI navigation approaches aim to improve Whole-Slide Image (WSI) diagnosis by modeling spatial exploration and selecting diagnostically relevant regions, yet most operate at…
MVR: Multi-view Video Reward Shaping for Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +3
Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language mod…
AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
Xian Zhang, Zexi Wu, Zinuo Li +5
Understanding long-form videos remains a significant challenge for vision--language models (VLMs) due to their extensive temporal length and high information density. Most current…