Lin Zhao

Machine learning quantifies dew formation mechanisms across China’s climate gradients

Zhe Li, Lin Zhao, Hanbo Ren, Ranmao Yang, Xinxin Li, Zhijiang Zhang, et al.

Short-term electricity consumption forecasting for low-altitude economy enterprises: A metaheuristic-optimized efficient robust neural network approach

Yujin Zhu, Yuwei Wang, Zhuoxuan Li, Kang Chen, Peng Wu, Lin Zhao, et al.

Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation

Yuqi Li, Xi Xiao, Yunbei Zhang, Lin Zhao, Yu Li, Aiden Zhao, et al.

Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adaptation, including Visual Prompt Tuning (VPT), provides a lightweight way to specialize these models, b…Read more

DB-VIO: Dual-Branch Visual Inertial Odometry with Enhanced Visual-Inertial Representation

Ziyu Wan, Lin Zhao

Visual inertial odometry (VIO) is essential for accurate 6-DoF motion estimation in mobile robotic systems. Recent learning-based VIO methods have shown promising progress, but they often rely on unified visual--inertial representations and a single temporal model for full-pose e…Read more

Joint On-and-Off Policy Learning for Vision-and-Language Navigation

Qingrong He, Lin Zhao, Kevin Zheng, Liang Lin

Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Recent advancements in Vision-Language Models (VLM) have propelled the development of VLM-based VLN methods with two predominant par…Read more

Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction

Janet Wang, Yunbei Zhang, Lin Zhao, Xi Xiao, Jihun Hamm, Xiao Wang

Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar values and large regions evolve smoothly over time. This makes much of the intermediate per-token computation redund…Read more