_version_ 1866909807441608704
author Chen, Zhe
Wang, Weiyun
Cao, Yue
Liu, Yangzhou
Gao, Zhangwei
Cui, Erfei
Zhu, Jinguo
Ye, Shenglong
Tian, Hao
Liu, Zhaoyang
Gu, Lixin
Wang, Xuehui
Li, Qingyun
Ren, Yiming
Chen, Zixuan
Luo, Jiapeng
Wang, Jiahao
Jiang, Tan
Wang, Bo
He, Conghui
Shi, Botian
Zhang, Xingcheng
Lv, Han
Wang, Yi
Shao, Wenqi
Chu, Pei
Tu, Zhongying
He, Tong
Wu, Zhiyong
Deng, Huipeng
Ge, Jiaye
Chen, Kai
Zhang, Kaipeng
Wang, Limin
Dou, Min
Lu, Lewei
Zhu, Xizhou
Lu, Tong
Lin, Dahua
Qiao, Yu
Dai, Jifeng
Wang, Wenhai
author_facet Chen, Zhe
Wang, Weiyun
Cao, Yue
Liu, Yangzhou
Gao, Zhangwei
Cui, Erfei
Zhu, Jinguo
Ye, Shenglong
Tian, Hao
Liu, Zhaoyang
Gu, Lixin
Wang, Xuehui
Li, Qingyun
Ren, Yiming
Chen, Zixuan
Luo, Jiapeng
Wang, Jiahao
Jiang, Tan
Wang, Bo
He, Conghui
Shi, Botian
Zhang, Xingcheng
Lv, Han
Wang, Yi
Shao, Wenqi
Chu, Pei
Tu, Zhongying
He, Tong
Wu, Zhiyong
Deng, Huipeng
Ge, Jiaye
Chen, Kai
Zhang, Kaipeng
Wang, Limin
Dou, Min
Lu, Lewei
Zhu, Xizhou
Lu, Tong
Lin, Dahua
Qiao, Yu
Dai, Jifeng
Wang, Wenhai
contents We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL
format Preprint
id arxiv_https___arxiv_org_abs_2412_05271
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Chen, Zhe
Wang, Weiyun
Cao, Yue
Liu, Yangzhou
Gao, Zhangwei
Cui, Erfei
Zhu, Jinguo
Ye, Shenglong
Tian, Hao
Liu, Zhaoyang
Gu, Lixin
Wang, Xuehui
Li, Qingyun
Ren, Yiming
Chen, Zixuan
Luo, Jiapeng
Wang, Jiahao
Jiang, Tan
Wang, Bo
He, Conghui
Shi, Botian
Zhang, Xingcheng
Lv, Han
Wang, Yi
Shao, Wenqi
Chu, Pei
Tu, Zhongying
He, Tong
Wu, Zhiyong
Deng, Huipeng
Ge, Jiaye
Chen, Kai
Zhang, Kaipeng
Wang, Limin
Dou, Min
Lu, Lewei
Zhu, Xizhou
Lu, Tong
Lin, Dahua
Qiao, Yu
Dai, Jifeng
Wang, Wenhai
Computer Vision and Pattern Recognition
We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL
title Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.05271