Towards a Robust Retrieval-Based Summarization System

1 code implementation • 29 Mar 2024 • ShengJie Liu, Jing Wu, Jingyuan Bao, Wenyi Wang, Naira Hovakimyan, Christopher G Healey

SummRAG is an example of our goal of defining structured methods to test the capabilities of an LLM, rather than addressing issues in a one-off fashion.

Retrieval

SwitchTab: Switched Autoencoders Are Effective Tabular Learners

no code implementations • 4 Jan 2024 • Jing Wu, Suiyao Chen, Qi Zhao, Renat Sergazinov, Chen Li, ShengJie Liu, Chongchao Zhao, Tianpei Xie, Hanqing Guo, Cheng Ji, Daniel Cociorva, Hakan Brunzel

Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies.

Representation Learning

Is Knowledge All Large Language Models Needed for Causal Reasoning?

1 code implementation • 30 Dec 2023 • Hengrui Cai, ShengJie Liu, Rui Song

This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence.

counterfactual

Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review

1 code implementation • 5 May 2023 • Chuang Zhu, ShengJie Liu, Zekuan Yu, Feng Xu, Arpit Aggarwal, Germán Corredor, Anant Madabhushi, Qixun Qu, Hongwei Fan, Fangda Li, Yueheng Li, Xianchao Guan, Yongbing Zhang, Vivek Kumar Singh, Farhan Akram, Md. Mostafa Kamal Sarker, Zhongyue Shi, Mulan Jin

For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue to formulate a precise treatment plan.

Image Generation SSIM

Multidimensional Graph Neural Networks for Wireless Communications

1 code implementation • 22 Dec 2022 • ShengJie Liu, Jia Guo, Chenyang Yang

Based on the observation that the mismatched permutation property from the policies and the information loss during the update of hidden representations have large impact on the learning performance and efficiency, in this paper we propose a unified framework to learn permutable wireless policies with multidimensional GNNs.

WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels

1 code implementation • 5 Oct 2022 • ShengJie Liu, Chuang Zhu, Wenqi Tang

For scenarios where weak supervision and cross-domain problems coexist, this paper defines a new task: unsupervised domain adaptation based on weak source domain labels (WUDA).

Image Segmentation object-detection +5

BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix

1 code implementation • 25 Apr 2022 • ShengJie Liu, Chuang Zhu, Feng Xu, Xinyu Jia, Zhongyue Shi, Mulan Jin

The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer.

Breast Cancer Detection Classification Of Breast Cancer Histology Images +4

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

1 code implementation • 24 Aug 2021 • Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, ShengJie Liu, Wenli Zhou

It is very challenging for various visual tasks such as image fusion, pedestrian detection and image-to-image translation in low light conditions due to the loss of effective target areas.

Image Registration Image-to-Image Translation +6