no code implementations • 28 May 2024 • Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu
Methodologically, we propose a resource-efficiency Hopfield retriever to enhance the efficiency and accuracy of conversational information retrieval within our actions.
no code implementations • 22 May 2024 • Zhenyu Pan, Yoonsung Jeong, Xiaoda Liu, Han Liu
We propose a heterogeneous graph mamba network (HGMN) as the first exploration in leveraging the selective state space models (SSSMs) for heterogeneous graph learning.
no code implementations • 26 Mar 2024 • Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu
We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA).
no code implementations • 5 Mar 2024 • Zhenyu Pan, Ammar Gilani, En-Jui Kuo, Zhuo Liu
We propose an RNN-based efficient Ising model solver, the Criticality-ordered Recurrent Mean Field (CoRMF), for forward Ising problems.