4 papers
Iterate on an LLM, Serve on an SLM
Keegan Wang
As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities but have largely been able to…
Hierarchical Action Learning for Weakly-Supervised Action Segmentation
Junxian Huang, Ruichu Cai, Hao Zhu +5
Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This…
TEA: Temporal Adaptive Satellite Image Semantic Segmentation
Juyuan Kang, Hao Zhu, Yan Zhu +6
Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. E…
Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation
Hao Zhu, Yan Zhu, Jiayu Xiao +4
Automated crop mapping through Satellite Image Time Series (SITS) has emerged as a crucial avenue for agricultural monitoring and management. However, due to the low resolution and…