{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/infinity-mm-scaling-multimodal-performance","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","arxiv_id":"2410.18558","date":"2024-10-24","proceeding":null,"authors":["Shuhao Gu","Jialing Zhang","Siyuan Zhou","Kevin Yu","Zhaohu Xing","Liangdong Wang","Zhou Cao","Jintao Jia","Zhuoyi Zhang","YiXuan Wang","Zhenchong Hu","Bo-Wen Zhang","Jijie Li","Dong Liang","Yingli Zhao","Songjing Wang","Yulong Ao","Yiming Ju","Huanhuan Ma","Xiaotong Li","Haiwen Diao","Yufeng Cui","Xinlong Wang","Yaoqi Liu","Fangxiang Feng","Guang Liu"],"abstract":"Recently, Vision-Language Models (VLMs) have achieved remarkable progress in multimodal tasks, and multimodal instruction data serves as the foundation for enhancing VLM capabilities. Despite the availability of several open-source multimodal datasets, limitations in the scale and quality of open-source instruction data hinder the performance of VLMs trained on these datasets, leading to a significant gap compared to models trained on closed-source data. To address this challenge, we introduce Infinity-MM, a large-scale multimodal instruction dataset. We collected the available multimodal instruction datasets and performed unified preprocessing, resulting in a dataset with over 40 million samples that ensures diversity and accuracy. Furthermore, to enable large-scale expansion of instruction data and support the continuous acquisition of high-quality data, we propose a synthetic instruction generation method based on a tagging system and open-source VLMs. By establishing correspondences between different types of images and associated instruction types, this method can provide essential guidance during data synthesis. Leveraging this high-quality data, we have trained a 2-billion-parameter Vision-Language Model, Aquila-VL-2B, which achieves state-of-the-art (SOTA) performance among models of similar scale. The data is available at: https://huggingface.co/datasets/BAAI/Infinity-MM.","url_abs":"https://arxiv.org/abs/2410.18558v2","url_pdf":"https://arxiv.org/pdf/2410.18558v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"infinity-mm-scaling-multimodal-performance","repo_url":"https://github.com/LLaVA-VL/LLaVA-NeXT","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"infinity-mm-scaling-multimodal-performance","repo_url":"https://github.com/flagopen/flagscale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"infinity-mm-scaling-multimodal-performance","repo_url":"https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"infinity-mm-scaling-multimodal-performance","repo_url":"https://huggingface.co/datasets/BAAI/Infinity-MM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"infinity-mm","name":"Infinity-MM","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-textatlaseval","task":"Image Generation","dataset":"TextAtlasEval","model":"Infinity-2B","rank_in_archive_order":4,"of":7,"metrics":{"StyledTextSynth Clip Score":"0.2727","StyledTextSynth FID":"84.95","StyledTextSynth OCR (Accuracy)":"0.80","StyledTextSynth OCR (Cer)":"0.93","StyledTextSynth OCR (F1 Score)":"1.42","TextScenesHQ Clip Score":"0.2346","TextScenesHQ FID":"71.59","TextScenesHQ OCR (Accuracy)":"1.06","TextScenesHQ OCR (Cer)":"0.88","TextScenesHQ OCR (F1 Score)":"1.74","TextVisionBlend Clip Score":"0.1979","TextVisionBlend FID":"95.69","TextVisionBlend OCR (Accuracy)":"2.98","TextVisionBlend OCR (Cer)":"0.83","TextVsionBlend OCR (F1 Score)":"3.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.18558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18558"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://huggingface.co/datasets/BAAI/Infinity-MM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flagopen/flagscale","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LLaVA-VL/LLaVA-NeXT","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0d33aaf712b41133","entry":"auto_remote","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/serve/core.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/serve/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d33aaf712b41133"}},{"code_sha256_prefix":"a946897a635a9ffa","entry":"flatten_dict_to_args","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/utils.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a946897a635a9ffa"}},{"code_sha256_prefix":"6c1f969a5ed98237","entry":"make_headers","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/eval/robo.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/eval/robo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c1f969a5ed98237"}},{"code_sha256_prefix":"9dd40bc51eb5b8b0","entry":"prepare_compress_methods","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/compress/combined_algo.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/compress/combined_algo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9dd40bc51eb5b8b0"}},{"code_sha256_prefix":"ac0e60d70c14acfa","entry":"prepare_config","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/compress/compressor.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/compress/compressor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac0e60d70c14acfa"}},{"code_sha256_prefix":"e580a09ddd5d3d19","entry":"start_server","repo":"flagopen/flagscale","repo_kind":"listed","path":"flagscale/eval/robo.py","file_url":"https://github.com/flagopen/flagscale/blob/HEAD/flagscale/eval/robo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e580a09ddd5d3d19"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}