1 code implementation • 14 Feb 2024 • Yihao Fang, Stephen W. Thomas, Xiaodan Zhu
With the widespread adoption of large language models (LLMs) in numerous applications, the challenge of factuality and the propensity for hallucinations raises significant concerns.
1 code implementation • 25 Aug 2023 • Yihao Fang, Xianzhi Li, Stephen W. Thomas, Xiaodan Zhu
Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text.
Ranked #1 on Open Intent Detection on StackOverflow_CG
no code implementations • 16 Feb 2023 • Yihao Fang, Ilsang Ohn, Vijay Gupta, Lizhen Lin
We propose extrinsic and intrinsic deep neural network architectures as general frameworks for deep learning on manifolds.
no code implementations • 21 Dec 2022 • Yihao Fang, Mu Niu, Pokman Cheung, Lizhen Lin
We propose an extrinsic Bayesian optimization (eBO) framework for general optimization problems on manifolds.
no code implementations • 26 Oct 2022 • Sudhandar Balakrishnan, Yihao Fang, Xioadan Zhu
The invention of transformer-based models such as BERT, GPT, and RoBERTa has enabled researchers and financial companies to finetune these powerful models and use them in different downstream tasks to achieve state-of-the-art performance.
no code implementations • 4 Sep 2021 • Ziqing Hu, Yihao Fang, Lizhen Lin
In this work, we propose to train a graph neural network via resampling from a graphon estimate obtained from the underlying network data.
1 code implementation • 21 Aug 2020 • Mohammad Rasool Izadi, Yihao Fang, Robert Stevenson, Lizhen Lin
In this work, we propose to employ information-geometric tools to optimize a graph neural network architecture such as the graph convolutional networks.
Ranked #1 on Node Classification on Cora
no code implementations • 3 Jul 2020 • Yihao Fang, Shervin Manzuri Shalmani, Rong Zheng
Inference of uncompressed large scale DNN models can only run in the cloud with extra communication latency back and forth between cloud and end devices, while compressed DNN models achieve real-time inference on end devices at the price of lower predictive accuracy.
no code implementations • 7 Sep 2018 • Yihao Fang, Rong Zheng, Xiaodan Zhu
A novel logographic subword model is proposed to reinterpret logograms as abstract subwords for neural machine translation.