5 papers
Any to Full: Prompting Depth Anything for Depth Completion in One Stage
Zhiyuan Zhou, Ruofeng Liu, Taichi Liu +4
Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-f…
WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models
Anlan Yu, Zaishu Chen, Peili Song +6
Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies could drive robots into uns…
MuST2-Learn: Multi-view Spatial-Temporal-Type Learning for Heterogeneous Municipal Service Time Estimation
Nadia Asif, Zhiqing Hong, Shaogang Ren +3
Non-emergency municipal services such as city 311 systems have been widely implemented across cities in Canada and the United States to enhance residents' quality of life. These sy…
AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data
Qinchen Yang, Zhiqing Hong, Dongjiang Cao +6
Textual description of a physical location, commonly known as an address, plays an important role in location-based services(LBS) such as on-demand delivery and navigation. However…
Variational Language Concepts for Interpreting Foundation Language Models
Hengyi Wang, Shiwei Tan, Zhiqing Hong +2
Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of FLMs has primarily…