{"work":{"id":"3714835e-c5a6-4d7e-950c-be44670ed9e6","openalex_id":"https://openalex.org/W4395687490","doi":"10.48550/arxiv.2404.16821","arxiv_id":"2404.16821","raw_key":null,"title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","authors":null,"authors_text":"Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui","year":2024,"venue":"cs.CV","abstract":"In this report, we introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements: (1) Strong Vision Encoder: we explored a continuous learning strategy for the large-scale vision foundation model -- InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs. (2) Dynamic High-Resolution: we divide images into tiles ranging from 1 to 40 of 448$\\times$448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input. (3) High-Quality Bilingual Dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images, and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in OCR- and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks. Code has been released at https://github.com/OpenGVLab/InternVL.","external_url":"https://arxiv.org/abs/2404.16821","cited_by_count":16,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2404.16821","created_at":"2026-05-09T06:50:40.193956+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","render_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites"},"hub":{"state":{"work_id":"3714835e-c5a6-4d7e-950c-be44670ed9e6","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":67,"external_cited_by_count":16,"distinct_field_count":8,"first_pith_cited_at":"2024-04-22T14:32:33+00:00","last_pith_cited_at":"2026-06-30T04:08:22+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T04:09:31.300121+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":20},{"context_role":"baseline","n":4},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":19},{"context_polarity":"baseline","n":4},{"context_polarity":"use_method","n":2},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}