Search

Your search keyword '"Niu, Zhiyuan"' showing total 269 results
Start Over Author "Niu, Zhiyuan" Publication Year Range Last 50 years
269 results on '"Niu, Zhiyuan"'

2. OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue

Author

Gao, Weihao, Deng, Zhuo, Niu, Zhiyuan, Rong, Fuju, Chen, Chucheng, Gong, Zheng, Zhang, Wenze, Xiao, Daimin, Li, Fang, Cao, Zhenjie, Ma, Zhaoyi, Wei, Wenbin, and Ma, Lan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Large multimodal language models (LMMs) have achieved significant success in general domains. However, due to the significant differences between medical images and text and general web content, the performance of LMMs in medical scenarios is limited. In ophthalmology, clinical diagnosis relies on multiple modalities of medical images, but unfortunately, multimodal ophthalmic large language models have not been explored to date. In this paper, we study and construct an ophthalmic large multimodal model. Firstly, we use fundus images as an entry point to build a disease assessment and diagnosis pipeline to achieve common ophthalmic disease diagnosis and lesion segmentation. Then, we establish a new ophthalmic multimodal instruction-following and dialogue fine-tuning dataset based on disease-related knowledge data and publicly available real-world medical dialogue. We introduce visual ability into the large language model to complete the ophthalmic large language and vision assistant (OphGLM). Our experimental results demonstrate that the OphGLM model performs exceptionally well, and it has the potential to revolutionize clinical applications in ophthalmology. The dataset, code, and models will be made publicly available at https://github.com/ML-AILab/OphGLM., Comment: OphGLM:The first ophthalmology large language-and-vision assistant based on instructions and dialogue

Published
2023

3. Enhancing LM’s Task Adaptability: Powerful Post-training Framework with Reinforcement Learning from Model Feedback

Author

Rong, Fuju, Gao, Weihao, Deng, Zhuo, Gong, Zheng, Chen, Chucheng, Zhang, Wenze, Niu, Zhiyuan, Li, Fang, Ma, Lan, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Wand, Michael, editor, Malinovská, Kristína, editor, Schmidhuber, Jürgen, editor, and Tetko, Igor V., editor

Published
2024
Full Text
View/download PDF

24. An Interactive Mixed Reality Platform for Bedside Surgical Procedures

Author

Azimi, Ehsan, Niu, Zhiyuan, Stiber, Maia, Greene, Nicholas, Liu, Ruby, Molina, Camilo, Huang, Judy, Huang, Chien-Ming, Kazanzides, Peter, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Martel, Anne L., editor, Abolmaesumi, Purang, editor, Stoyanov, Danail, editor, Mateus, Diana, editor, Zuluaga, Maria A., editor, Zhou, S. Kevin, editor, Racoceanu, Daniel, editor, and Joskowicz, Leo, editor

Published
2020
Full Text
View/download PDF

27. Research on Gas Recognition Based on Gas Sensor Array and Feature Analysis

Author

Quan, Hao, Sun, Jianhai, Zhou, Tianye, Chen, Tingting, Niu, Zhiyuan, and Ma, Xibo

Abstract

In this work, a sensor array consisting of four sensors is designed. Detection of any mixture concentration in the range of 0–450 ppm hydrogen, 0–450 ppm ethylene, and 0–450 ppm carbon monoxide were achieved. Filter processing reduces the influence of sensor noise and ensures high recognition accuracy. Then, a total of 48 features such as response value, time feature, and first- and second-order features of sensor resistance were extracted from four sensors in each sample. In this article, the first- and second-order features are creatively proposed, which have a significant impact on the accuracy of the later model. It is found that gradient boosting decision tree (GBDT) has the highest classification accuracy, reaching 100%. Compared to models trained using only the first 180 s of data, gas prediction can be achieved at the initial sensor response stage, and the GBDT model has a preparation rate of up to 99.64%. To study the influence of different features on the sensor, the feature contribution of selected features in GBDT method is described. For the classification tasks, response time, recovery time, and second-order features contribute the most. Finally, the regression designed by GBDT method has a root-mean-square error of 23.52 ppm and an accuracy of 94.77%. This method did not require a lot of calculation and was suitable for running in small-embedded devices.

Published
2024
Full Text
View/download PDF

42. GmEID1 modulates light signaling through the Evening Complex to control flowering time and yield in soybean

Author

Qin, Chao, primary, Li, Haiyang, additional, Zhang, Shengrui, additional, Lin, Xiaoya, additional, Jia, Zhiwei, additional, Zhao, Fen, additional, Wei, Xiuzhi, additional, Jiao, Yuanchen, additional, Li, Zhuang, additional, Niu, Zhiyuan, additional, Zhou, Yonggang, additional, Li, Xiaojiao, additional, Li, Hongyu, additional, Zhao, Tao, additional, Liu, Jun, additional, Li, Haiyan, additional, Lu, Yuping, additional, Kong, Fanjiang, additional, and Liu, Bin, additional

Published
2023
Full Text
View/download PDF

45. An inquiry into urban carrying capacity of sustainable development demonstration belt of China: Multiscale evaluation and multidimensional interaction.

Author

Tan, Feifei, Gong, Chunyan, Niu, Zhiyuan, and Zhao, Yuxuan

Subjects
CAPACITY building, ECOLOGICAL carrying capacity, SCIENTIFIC method, AUTOREGRESSIVE models, INDUSTRIAL organization (Economic theory), SUSTAINABLE urban development, SUSTAINABLE development
Abstract

How to seek multiregional sustainable development within planetary boundaries depends on the scientific inquiry into urban carrying capacity from multiscale evaluation and multidimensional interaction. Using a typical region moving forward on the sustainable development demonstration belt of China, the Yangtze River Economic Belt (YREB), as a case study, a new integrated framework of multiscale evaluation and multidimensional interaction is proposed to track the urban comprehensive carrying capacity. We made a multiscale comprehensive assessment and constructed a panel vector autoregressive model for giving dissection on the drivers of urban carrying capacity and the qualitative and quantitative interaction from multidimensional variations. Results show that (1) the urban carrying capacity of China's YREB and its three reaches harbors an upward trend over time although there are uneven development patterns of inter‐regional and inter‐dimensional urban carrying capacity; (2) factor market carrying capacity (FMCC) is the critical driving force among four dimensions of urban carrying capacity, which has promotion effects on ecological environment carrying capacity (EECC) and industrial economics carrying capacity, but an inhibiting effect on transportation carrying capacity (TCC). (3) FMCC is the Granger cause of TCC, and there is a bidirectional Granger causality between the dimensions of FMCC and EECC; (4) each dimension is self‐supporting and influenced by its fluctuations. Tracking the underlying factors of urban carrying capacity can help construct an early‐warning mechanism when confronting the challenge of sustainable development and play a guiding role in both academic and practical aspects. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results