Search

Your search keyword '"Yang, Xinyue"' showing total 835 results
Start Over Author "Yang, Xinyue"
835 results on '"Yang, Xinyue"'

1. VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Author

Liu, Xiao, Zhang, Tianjie, Gu, Yu, Iong, Iat Long, Xu, Yifan, Song, Xixuan, Zhang, Shudan, Lai, Hanyu, Liu, Xinyi, Zhao, Hanlin, Sun, Jiadai, Yang, Xinyue, Yang, Yu, Qi, Zehan, Yao, Shuntian, Sun, Xueqiao, Cheng, Siyi, Zheng, Qinkai, Yu, Hao, Zhang, Hanchen, Hong, Wenyi, Ding, Ming, Pan, Lihang, Gu, Xiaotao, Zeng, Aohan, Du, Zhengxiao, Song, Chan Hee, Su, Yu, Dong, Yuxiao, and Tang, Jie

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

Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual foundation agents across diverse scenarios, including Embodied, Graphical User Interface, and Visual Design, with tasks formulated to probe the depth of LMMs' understanding and interaction capabilities. Through rigorous testing across nine proprietary LMM APIs and eight open models, we demonstrate the considerable yet still developing agent capabilities of these models. Additionally, VAB constructs a trajectory training set constructed through hybrid methods including Program-based Solvers, LMM Agent Bootstrapping, and Human Demonstrations, promoting substantial performance improvements in LMMs through behavior cloning. Our work not only aims to benchmark existing models but also provides a solid foundation for future development into visual foundation agents. Code, train \& test data, and part of fine-tuned open LMMs are available at \url{https://github.com/THUDM/VisualAgentBench}.

Published
2024

2. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Author

GLM, Team, Zeng, Aohan, Xu, Bin, Wang, Bowen, Zhang, Chenhui, Yin, Da, Zhang, Dan, Rojas, Diego, Feng, Guanyu, Zhao, Hanlin, Lai, Hanyu, Yu, Hao, Wang, Hongning, Sun, Jiadai, Zhang, Jiajie, Cheng, Jiale, Gui, Jiayi, Tang, Jie, Zhang, Jing, Sun, Jingyu, Li, Juanzi, Zhao, Lei, Wu, Lindong, Zhong, Lucen, Liu, Mingdao, Huang, Minlie, Zhang, Peng, Zheng, Qinkai, Lu, Rui, Duan, Shuaiqi, Zhang, Shudan, Cao, Shulin, Yang, Shuxun, Tam, Weng Lam, Zhao, Wenyi, Liu, Xiao, Xia, Xiao, Zhang, Xiaohan, Gu, Xiaotao, Lv, Xin, Liu, Xinghan, Liu, Xinyi, Yang, Xinyue, Song, Xixuan, Zhang, Xunkai, An, Yifan, Xu, Yifan, Niu, Yilin, Yang, Yuantao, Li, Yueyan, Bai, Yushi, Dong, Yuxiao, Qi, Zehan, Wang, Zhaoyu, Yang, Zhen, Du, Zhengxiao, Hou, Zhenyu, and Wang, Zihan

Subjects
Computer Science - Computation and Language
Abstract

We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes GLM-4, GLM-4-Air, and GLM-4-9B. They represent our most capable models that are trained with all the insights and lessons gained from the preceding three generations of ChatGLM. To date, the GLM-4 models are pre-trained on ten trillions of tokens mostly in Chinese and English, along with a small set of corpus from 24 languages, and aligned primarily for Chinese and English usage. The high-quality alignment is achieved via a multi-stage post-training process, which involves supervised fine-tuning and learning from human feedback. Evaluations show that GLM-4 1) closely rivals or outperforms GPT-4 in terms of general metrics such as MMLU, GSM8K, MATH, BBH, GPQA, and HumanEval, 2) gets close to GPT-4-Turbo in instruction following as measured by IFEval, 3) matches GPT-4 Turbo (128K) and Claude 3 for long context tasks, and 4) outperforms GPT-4 in Chinese alignments as measured by AlignBench. The GLM-4 All Tools model is further aligned to understand user intent and autonomously decide when and which tool(s) touse -- including web browser, Python interpreter, text-to-image model, and user-defined functions -- to effectively complete complex tasks. In practical applications, it matches and even surpasses GPT-4 All Tools in tasks like accessing online information via web browsing and solving math problems using Python interpreter. Over the course, we have open-sourced a series of models, including ChatGLM-6B (three generations), GLM-4-9B (128K, 1M), GLM-4V-9B, WebGLM, and CodeGeeX, attracting over 10 million downloads on Hugging face in the year 2023 alone. The open models can be accessed through https://github.com/THUDM and https://huggingface.co/THUDM.

Published
2024

10. Random Mask Perturbation Based Explainable Method of Graph Neural Networks

Author

Yang, Xinyue, Huang, Hai, Zuo, Xingquan, 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, Yang, De-Nian, editor, Xie, Xing, editor, Tseng, Vincent S., editor, Pei, Jian, editor, Huang, Jen-Wei, editor, and Lin, Jerry Chun-Wei, editor

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results