1 code implementation • 1 Apr 2024 • Boran Han, Shuai Zhang, Xingjian Shi, Markus Reichstein
A key discovery of our research is that representations derived from natural images are not always compatible with the distinct characteristics of geospatial remote sensors, underscoring the limitations of existing representations in this field.
no code implementations • 8 Mar 2024 • Wenqi Jiang, Shuai Zhang, Boran Han, Jie Wang, Bernie Wang, Tim Kraska
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases.
no code implementations • 6 Jan 2024 • Yixin Chen, Shuai Zhang, Boran Han, Tong He, Bo Li
In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs).
Ranked #50 on Visual Question Answering on MM-Vet
no code implementations • 8 Oct 2023 • Yixin Chen, Shuai Zhang, Boran Han, Jiaya Jia
In-context learning (ICL) involves reasoning from given contextual examples.
1 code implementation • NeurIPS 2023 • Zhihan Gao, Xingjian Shi, Boran Han, Hao Wang, Xiaoyong Jin, Danielle Maddix, Yi Zhu, Mu Li, Yuyang Wang
We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset.
1 code implementation • 30 May 2023 • Boran Han
The class-wise distribution of angular representation becomes a sum of these kernels.
2 code implementations • ICCV 2023 • Matias Mendieta, Boran Han, Xingjian Shi, Yi Zhu, Chen Chen
Geospatial technologies are becoming increasingly essential in our world for a wide range of applications, including agriculture, urban planning, and disaster response.
no code implementations • 8 Jan 2022 • Jiahe Wang, Boran Han
Microscopy imaging is vital in biology research and diagnosis.