Search

Your search keyword '"Xu, Jialu"' showing total 536 results
Start Over Author "Xu, Jialu"
536 results on '"Xu, Jialu"'

7. PandaGPT: One Model To Instruction-Follow Them All

Author

Su, Yixuan, Lan, Tian, Li, Huayang, Xu, Jialu, Wang, Yan, and Cai, Deng

Subjects
Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition
Abstract

We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna. Notably, only aligned image-text pairs are required for the training of PandaGPT. Thanks to the strong capability of ImageBind in embedding data from different modalities into the same space, PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU). We hope that PandaGPT serves as an initial step toward building AGI that can perceive and understand inputs in different modalities holistically, as we humans do. Our project page is at https://panda-gpt.github.io/., Comment: Technical report, work in progress. Our project page is at https://panda-gpt.github.io/

Published
2023

10. An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation

Author

Su, Yixuan and Xu, Jialu

Subjects
Computer Science - Computation and Language
Abstract

In the study, we empirically compare the two recently proposed decoding methods, i.e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation. The automatic evaluation results suggest that, while CS performs worse than CD on the MAUVE metric, it substantially surpasses CD on the diversity and coherence metrics. More notably, extensive human evaluations across three different domains demonstrate that human annotators are universally more in favor of CS over CD with substantial margins. The contradicted results between MAUVE and human evaluations reveal that MAUVE does not accurately reflect human preferences. Therefore, we call upon the research community to develop better evaluation metrics for open-ended text generation. To ensure the reproducibility of our work, we have open-sourced all our code, evaluation results, as well as human annotations at https://github.com/yxuansu/Contrastive_Search_versus_Contrastive_Decoding., Comment: Technical report with 9 pages, 5 tables, and 6 figures

Published
2022

23. The Female Writing of Quiet and Profound: Chantal Akerman’s Films in the Perspective of Feminism

Author

Hao, Xinran, Liu, Xiaoge, Xu, Jialu, Yang, Jiancheng, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Majoul, Bootheina, editor, Pandya, Digvijay, editor, and Wang, Lin, editor

Published
2023
Full Text
View/download PDF

38. Motor Imagery Intention Recognition Based on Common Spatial Pattern for Manipulator Grasping

Author

Li, Wenjie, Xu, Jialu, Yan, Xiaoyu, Lin, Chengyu, Fu, Chenglong, Goos, Gerhard, Founding 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, Liu, Honghai, editor, Yin, Zhouping, editor, Liu, Lianqing, editor, Jiang, Li, editor, Gu, Guoying, editor, Wu, Xinyu, editor, and Ren, Weihong, editor

Published
2022
Full Text
View/download PDF

43. Assessment of Multiple Planetary Boundary Layer Height Retrieval Methods and Their Impact on PM 2.5 and Its Chemical Compositions throughout a Year in Nanjing.

Author

Han, Zhanghanshu, Wang, Yuying, Xu, Jialu, Shang, Yi, Li, Zhanqing, Lu, Chunsong, Zhan, Puning, Song, Xiaorui, Lv, Min, and Yang, Yinshan

Subjects
ATMOSPHERIC boundary layer, AIR pollution, MICROWAVE radiometers, PARTICULATE matter, AEROSOLS
Abstract

In this study, we investigate the planetary boundary layer height (PBLH) using micro-pulse lidar (MPL) and microwave radiometer (MWR) methods, examining its relationship with the mass concentration of particles less than 2.5 µm in aerodynamic diameter (PM2.5) and its chemical compositions. Long-term PBLH retrieval results are presented derived from the MPL and the MWR, including its seasonal and diurnal variations, showing a superior performance regarding the MPL in terms of reliability and consistency with PM2.5. Also examined are the relationships between the two types of PBLHs and PM2.5. Unlike the PBLH derived from the MPL, the PBLH derived from the MWR does not have a negative correlation under severe pollution conditions. Furthermore, this study explores the effects of the PBLH on different aerosol chemical compositions, with the most pronounced impact observed on primary aerosols and relatively minimal influence on secondary aerosols, especially secondary organics during spring. This study underscores disparities in PBLH retrievals by different instruments during long-term observations and unveils distinct relationships between the PBLH and aerosol chemical compositions. Moreover, it highlights the greater influence of the PBLH on primary pollutants, laying the groundwork for future research in this field. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

44. Isolation of anthraquinone derivatives from Rubia cordifolia (Rubiaceae) and their bioactivities against plant pathogenic microorganisms.

Author

Wang, Wenhao, Guo, Yifei, Xu, Jialu, Zhang, Hao, Ma, Zhiqing, and Wu, Hua

Subjects
BOTANICAL fungicides, TOBACCO mosaic virus, PHYTOPATHOGENIC microorganisms, ANTHRAQUINONE derivatives, PHYTOPHTHORA capsici
Abstract

BACKGROUND: The discovery of antimicrobial ingredients from natural products could be an effective way to create novel fungicides. Rubia cordifolia L., a traditional Chinese herb, may have antimicrobial effects on plant pathogens according to our previous screening study. RESULTS: Rubia cordifolia L. extracts had moderate inhibitory effects on apple Valsa canker (Valsa mali) and tomato grey mould (Botrytis cinerea) at a concentration of 10 mg mL−1. With the use of bioguided isolation methods, eight compounds (1–8) were obtained, including the new compound 2,2,6‐trimethyl‐6‐(4‐methylphenyl)‐tetrahydropyrano‐ 3‐ol (7), and seven quinone derivatives. Two compounds, mollugin (1) and 1,3,6‐trihydroxy‐2‐methylanthraquinone (6), were found to exhibit outstanding antifungal activities against V. mali and Phytophthora capsici Leon. The half maximal effective concentration (EC50) of compound 1 and compound 6 against V. mali were 79.08 and 81.78 μg mL−1, respectively, and the EC50 of compound 6 against P. capsici was 4.86 μg mL−1. Compound 1 also showed excellent activity against tobacco mosaic virus (TMV). The inactive, inductive, protective and curative activities against TMV were 84.29%, 83.38%, 86.81%, and 60.02%, respectively, at a concentration of 500 μg mL−1, which were all close to or greater than that of the positive control (100 μg mL−1 chitosan oligosaccharide, COS). CONCLUSION: Mollugin and 1,3,6‐trihydroxy‐2‐methylanthraquinone are potentially valuable active compounds that lay a foundation for research on botanical fungicide products derived from R. cordifolia L. and provide lead structures for quinone derivative synthesis and structural modification. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results