Staff View: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	Guo, Dong, Wu, Faming, Zhu, Feida, Leng, Fuxing, Shi, Guang, Chen, Haobin, Fan, Haoqi, Wang, Jian, Jiang, Jianyu, Wang, Jiawei, Chen, Jingji, Huang, Jingjia, Lei, Kang, Yuan, Liping, Luo, Lishu, Liu, Pengfei, Ye, Qinghao, Qian, Rui, Yan, Shen, Zhao, Shixiong, Peng, Shuai, Li, Shuangye, Yuan, Sihang, Wu, Sijin, Cheng, Tianheng, Liu, Weiwei, Wang, Wenqian, Zeng, Xianhan, Liu, Xiao, Qin, Xiaobo, Ding, Xiaohan, Xiao, Xiaojun, Zhang, Xiaoying, Zhang, Xuanwei, Xiong, Xuehan, Peng, Yanghua, Chen, Yangrui, Li, Yanwei, Hu, Yanxu, Lin, Yi, Hu, Yiyuan, Zhang, Yiyuan, Wu, Youbin, Li, Yu, Liu, Yudong, Ling, Yue, Qin, Yujia, Wang, Zanbo, He, Zhiwu, Zhang, Aoxue, Yi, Bairen, Liao, Bencheng, Huang, Can, Zhang, Can, Deng, Chaorui, Deng, Chaoyi, Lin, Cheng, Yuan, Cheng, Li, Chenggang, Gou, Chenhui, Lou, Chenwei, Wei, Chengzhi, Liu, Chundian, Li, Chunyuan, Zhu, Deyao, Zhong, Donghong, Li, Feng, Zhang, Feng, Wu, Gang, Li, Guodong, Xiao, Guohong, Lin, Haibin, Yang, Haihua, Wang, Haoming, Ji, Heng, Hao, Hongxiang, Shen, Hui, Li, Huixia, Li, Jiahao, Wu, Jialong, Zhu, Jianhua, Jiao, Jianpeng, Feng, Jiashi, Chen, Jiaze, Duan, Jianhui, Liu, Jihao, Zeng, Jin, Tang, Jingqun, Sun, Jingyu, Chen, Joya, Long, Jun, Feng, Junda, Zhan, Junfeng, Fang, Junjie, Lu, Junting, Hua, Kai, Liu, Kai, Shen, Kai, Zhang, Kaiyuan, Shen, Ke, Wang, Ke, Pan, Keyu, Zhang, Kun, Li, Kunchang, Li, Lanxin, Li, Lei, Shi, Lei, Han, Li, Xiang, Liang, Chen, Liangqiang, Chen, Lin, Li, Lin, Yan, Lin, Chi, Liying, Liu, Longxiang, Du, Mengfei, Wang, Mingxuan, Pan, Ningxin, Chen, Peibin, Chen, Pengfei, Wu, Pengfei, Yuan, Qingqing, Shuai, Qingyao, Tao, Qiuyan, Zheng, Renjie, Zhang, Renrui, Zhang, Ru, Wang, Rui, Yang, Rui, Zhao, Rui, Xu, Shaoqiang, Liang, Shihao, Yan, Shipeng, Zhong, Shu, Cao, Shuaishuai, Wu, Shuangzhi, Liu, Shufan, Chang, Shuhan, Cai, Songhua, Ao, Tenglong, Yang, Tianhao, Zhang, Tingting, Zhong, Wanjun, Jia, Wei, Weng, Wei, Yu, Weihao, Huang, Wenhao, Zhu, Wenjia, Yang, Wenli, Wang, Wenzhi, Long, Xiang, Yin, XiangRui, Li, Xiao, Zhu, Xiaolei, Jia, Xiaoying, Zhang, Xijin, Liu, Xin, Zhang, Xinchen, Yang, Xinyu, Luo, Xiongcai, Chen, Xiuli, Zhong, Xuantong, Xiao, Xuefeng, Li, Xujing, Wu, Yan, Wen, Yawei, Du, Yifan, Zhang, Yihao, Ye, Yining, Wu, Yonghui, Liu, Yu, Yue, Yu, Zhou, Yufeng, Yuan, Yufeng, Xu, Yuhang, Yang, Yuhong, Zhang, Yun, Fang, Yunhao, Li, Yuntao, Ren, Yurui, Xiong, Yuwen, Hong, Zehua, Wang, Zehua, Sun, Zewei, Wang, Zeyu, Cai, Zhao, Zha, Zhaoyue, An, Zhecheng, Zhao, Zhehui, Xu, Zhengzhuo, Chen, Zhipeng, Wu, Zhiyong, Zheng, Zhuofan, Wang, Zihao, Huang, Zilong, Zhu, Ziyu, Song, Zuquan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	https://arxiv.org/abs/2505.07062
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866913832004222976
author	Guo, Dong Wu, Faming Zhu, Feida Leng, Fuxing Shi, Guang Chen, Haobin Fan, Haoqi Wang, Jian Jiang, Jianyu Wang, Jiawei Chen, Jingji Huang, Jingjia Lei, Kang Yuan, Liping Luo, Lishu Liu, Pengfei Ye, Qinghao Qian, Rui Yan, Shen Zhao, Shixiong Peng, Shuai Li, Shuangye Yuan, Sihang Wu, Sijin Cheng, Tianheng Liu, Weiwei Wang, Wenqian Zeng, Xianhan Liu, Xiao Qin, Xiaobo Ding, Xiaohan Xiao, Xiaojun Zhang, Xiaoying Zhang, Xuanwei Xiong, Xuehan Peng, Yanghua Chen, Yangrui Li, Yanwei Hu, Yanxu Lin, Yi Hu, Yiyuan Zhang, Yiyuan Wu, Youbin Li, Yu Liu, Yudong Ling, Yue Qin, Yujia Wang, Zanbo He, Zhiwu Zhang, Aoxue Yi, Bairen Liao, Bencheng Huang, Can Zhang, Can Deng, Chaorui Deng, Chaoyi Lin, Cheng Yuan, Cheng Li, Chenggang Gou, Chenhui Lou, Chenwei Wei, Chengzhi Liu, Chundian Li, Chunyuan Zhu, Deyao Zhong, Donghong Li, Feng Zhang, Feng Wu, Gang Li, Guodong Xiao, Guohong Lin, Haibin Yang, Haihua Wang, Haoming Ji, Heng Hao, Hongxiang Shen, Hui Li, Huixia Li, Jiahao Wu, Jialong Zhu, Jianhua Jiao, Jianpeng Feng, Jiashi Chen, Jiaze Duan, Jianhui Liu, Jihao Zeng, Jin Tang, Jingqun Sun, Jingyu Chen, Joya Long, Jun Feng, Junda Zhan, Junfeng Fang, Junjie Lu, Junting Hua, Kai Liu, Kai Shen, Kai Zhang, Kaiyuan Shen, Ke Wang, Ke Pan, Keyu Zhang, Kun Li, Kunchang Li, Lanxin Li, Lei Shi, Lei Han, Li Xiang, Liang Chen, Liangqiang Chen, Lin Li, Lin Yan, Lin Chi, Liying Liu, Longxiang Du, Mengfei Wang, Mingxuan Pan, Ningxin Chen, Peibin Chen, Pengfei Wu, Pengfei Yuan, Qingqing Shuai, Qingyao Tao, Qiuyan Zheng, Renjie Zhang, Renrui Zhang, Ru Wang, Rui Yang, Rui Zhao, Rui Xu, Shaoqiang Liang, Shihao Yan, Shipeng Zhong, Shu Cao, Shuaishuai Wu, Shuangzhi Liu, Shufan Chang, Shuhan Cai, Songhua Ao, Tenglong Yang, Tianhao Zhang, Tingting Zhong, Wanjun Jia, Wei Weng, Wei Yu, Weihao Huang, Wenhao Zhu, Wenjia Yang, Wenli Wang, Wenzhi Long, Xiang Yin, XiangRui Li, Xiao Zhu, Xiaolei Jia, Xiaoying Zhang, Xijin Liu, Xin Zhang, Xinchen Yang, Xinyu Luo, Xiongcai Chen, Xiuli Zhong, Xuantong Xiao, Xuefeng Li, Xujing Wu, Yan Wen, Yawei Du, Yifan Zhang, Yihao Ye, Yining Wu, Yonghui Liu, Yu Yue, Yu Zhou, Yufeng Yuan, Yufeng Xu, Yuhang Yang, Yuhong Zhang, Yun Fang, Yunhao Li, Yuntao Ren, Yurui Xiong, Yuwen Hong, Zehua Wang, Zehua Sun, Zewei Wang, Zeyu Cai, Zhao Zha, Zhaoyue An, Zhecheng Zhao, Zhehui Xu, Zhengzhuo Chen, Zhipeng Wu, Zhiyong Zheng, Zhuofan Wang, Zihao Huang, Zilong Zhu, Ziyu Song, Zuquan
author_facet	Guo, Dong Wu, Faming Zhu, Feida Leng, Fuxing Shi, Guang Chen, Haobin Fan, Haoqi Wang, Jian Jiang, Jianyu Wang, Jiawei Chen, Jingji Huang, Jingjia Lei, Kang Yuan, Liping Luo, Lishu Liu, Pengfei Ye, Qinghao Qian, Rui Yan, Shen Zhao, Shixiong Peng, Shuai Li, Shuangye Yuan, Sihang Wu, Sijin Cheng, Tianheng Liu, Weiwei Wang, Wenqian Zeng, Xianhan Liu, Xiao Qin, Xiaobo Ding, Xiaohan Xiao, Xiaojun Zhang, Xiaoying Zhang, Xuanwei Xiong, Xuehan Peng, Yanghua Chen, Yangrui Li, Yanwei Hu, Yanxu Lin, Yi Hu, Yiyuan Zhang, Yiyuan Wu, Youbin Li, Yu Liu, Yudong Ling, Yue Qin, Yujia Wang, Zanbo He, Zhiwu Zhang, Aoxue Yi, Bairen Liao, Bencheng Huang, Can Zhang, Can Deng, Chaorui Deng, Chaoyi Lin, Cheng Yuan, Cheng Li, Chenggang Gou, Chenhui Lou, Chenwei Wei, Chengzhi Liu, Chundian Li, Chunyuan Zhu, Deyao Zhong, Donghong Li, Feng Zhang, Feng Wu, Gang Li, Guodong Xiao, Guohong Lin, Haibin Yang, Haihua Wang, Haoming Ji, Heng Hao, Hongxiang Shen, Hui Li, Huixia Li, Jiahao Wu, Jialong Zhu, Jianhua Jiao, Jianpeng Feng, Jiashi Chen, Jiaze Duan, Jianhui Liu, Jihao Zeng, Jin Tang, Jingqun Sun, Jingyu Chen, Joya Long, Jun Feng, Junda Zhan, Junfeng Fang, Junjie Lu, Junting Hua, Kai Liu, Kai Shen, Kai Zhang, Kaiyuan Shen, Ke Wang, Ke Pan, Keyu Zhang, Kun Li, Kunchang Li, Lanxin Li, Lei Shi, Lei Han, Li Xiang, Liang Chen, Liangqiang Chen, Lin Li, Lin Yan, Lin Chi, Liying Liu, Longxiang Du, Mengfei Wang, Mingxuan Pan, Ningxin Chen, Peibin Chen, Pengfei Wu, Pengfei Yuan, Qingqing Shuai, Qingyao Tao, Qiuyan Zheng, Renjie Zhang, Renrui Zhang, Ru Wang, Rui Yang, Rui Zhao, Rui Xu, Shaoqiang Liang, Shihao Yan, Shipeng Zhong, Shu Cao, Shuaishuai Wu, Shuangzhi Liu, Shufan Chang, Shuhan Cai, Songhua Ao, Tenglong Yang, Tianhao Zhang, Tingting Zhong, Wanjun Jia, Wei Weng, Wei Yu, Weihao Huang, Wenhao Zhu, Wenjia Yang, Wenli Wang, Wenzhi Long, Xiang Yin, XiangRui Li, Xiao Zhu, Xiaolei Jia, Xiaoying Zhang, Xijin Liu, Xin Zhang, Xinchen Yang, Xinyu Luo, Xiongcai Chen, Xiuli Zhong, Xuantong Xiao, Xuefeng Li, Xujing Wu, Yan Wen, Yawei Du, Yifan Zhang, Yihao Ye, Yining Wu, Yonghui Liu, Yu Yue, Yu Zhou, Yufeng Yuan, Yufeng Xu, Yuhang Yang, Yuhong Zhang, Yun Fang, Yunhao Li, Yuntao Ren, Yurui Xiong, Yuwen Hong, Zehua Wang, Zehua Sun, Zewei Wang, Zeyu Cai, Zhao Zha, Zhaoyue An, Zhecheng Zhao, Zhehui Xu, Zhengzhuo Chen, Zhipeng Wu, Zhiyong Zheng, Zhuofan Wang, Zihao Huang, Zilong Zhu, Ziyu Song, Zuquan
contents	We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)
format	Preprint
id	arxiv_https___arxiv_org_abs_2505_07062
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Seed1.5-VL Technical Report Guo, Dong Wu, Faming Zhu, Feida Leng, Fuxing Shi, Guang Chen, Haobin Fan, Haoqi Wang, Jian Jiang, Jianyu Wang, Jiawei Chen, Jingji Huang, Jingjia Lei, Kang Yuan, Liping Luo, Lishu Liu, Pengfei Ye, Qinghao Qian, Rui Yan, Shen Zhao, Shixiong Peng, Shuai Li, Shuangye Yuan, Sihang Wu, Sijin Cheng, Tianheng Liu, Weiwei Wang, Wenqian Zeng, Xianhan Liu, Xiao Qin, Xiaobo Ding, Xiaohan Xiao, Xiaojun Zhang, Xiaoying Zhang, Xuanwei Xiong, Xuehan Peng, Yanghua Chen, Yangrui Li, Yanwei Hu, Yanxu Lin, Yi Hu, Yiyuan Zhang, Yiyuan Wu, Youbin Li, Yu Liu, Yudong Ling, Yue Qin, Yujia Wang, Zanbo He, Zhiwu Zhang, Aoxue Yi, Bairen Liao, Bencheng Huang, Can Zhang, Can Deng, Chaorui Deng, Chaoyi Lin, Cheng Yuan, Cheng Li, Chenggang Gou, Chenhui Lou, Chenwei Wei, Chengzhi Liu, Chundian Li, Chunyuan Zhu, Deyao Zhong, Donghong Li, Feng Zhang, Feng Wu, Gang Li, Guodong Xiao, Guohong Lin, Haibin Yang, Haihua Wang, Haoming Ji, Heng Hao, Hongxiang Shen, Hui Li, Huixia Li, Jiahao Wu, Jialong Zhu, Jianhua Jiao, Jianpeng Feng, Jiashi Chen, Jiaze Duan, Jianhui Liu, Jihao Zeng, Jin Tang, Jingqun Sun, Jingyu Chen, Joya Long, Jun Feng, Junda Zhan, Junfeng Fang, Junjie Lu, Junting Hua, Kai Liu, Kai Shen, Kai Zhang, Kaiyuan Shen, Ke Wang, Ke Pan, Keyu Zhang, Kun Li, Kunchang Li, Lanxin Li, Lei Shi, Lei Han, Li Xiang, Liang Chen, Liangqiang Chen, Lin Li, Lin Yan, Lin Chi, Liying Liu, Longxiang Du, Mengfei Wang, Mingxuan Pan, Ningxin Chen, Peibin Chen, Pengfei Wu, Pengfei Yuan, Qingqing Shuai, Qingyao Tao, Qiuyan Zheng, Renjie Zhang, Renrui Zhang, Ru Wang, Rui Yang, Rui Zhao, Rui Xu, Shaoqiang Liang, Shihao Yan, Shipeng Zhong, Shu Cao, Shuaishuai Wu, Shuangzhi Liu, Shufan Chang, Shuhan Cai, Songhua Ao, Tenglong Yang, Tianhao Zhang, Tingting Zhong, Wanjun Jia, Wei Weng, Wei Yu, Weihao Huang, Wenhao Zhu, Wenjia Yang, Wenli Wang, Wenzhi Long, Xiang Yin, XiangRui Li, Xiao Zhu, Xiaolei Jia, Xiaoying Zhang, Xijin Liu, Xin Zhang, Xinchen Yang, Xinyu Luo, Xiongcai Chen, Xiuli Zhong, Xuantong Xiao, Xuefeng Li, Xujing Wu, Yan Wen, Yawei Du, Yifan Zhang, Yihao Ye, Yining Wu, Yonghui Liu, Yu Yue, Yu Zhou, Yufeng Yuan, Yufeng Xu, Yuhang Yang, Yuhong Zhang, Yun Fang, Yunhao Li, Yuntao Ren, Yurui Xiong, Yuwen Hong, Zehua Wang, Zehua Sun, Zewei Wang, Zeyu Cai, Zhao Zha, Zhaoyue An, Zhecheng Zhao, Zhehui Xu, Zhengzhuo Chen, Zhipeng Wu, Zhiyong Zheng, Zhuofan Wang, Zihao Huang, Zilong Zhu, Ziyu Song, Zuquan Computer Vision and Pattern Recognition Artificial Intelligence We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)
title	Seed1.5-VL Technical Report
topic	Computer Vision and Pattern Recognition Artificial Intelligence
url	https://arxiv.org/abs/2505.07062

Similar Items