{"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/long-vita-scaling-large-multi-modal-models-to","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray","arxiv_id":"2502.05177","date":"2025-02-07","proceeding":null,"authors":["Yunhang Shen","Chaoyou Fu","Shaoqi Dong","Xiong Wang","Peixian Chen","Mengdan Zhang","Haoyu Cao","Ke Li","Xiawu Zheng","Yan Zhang","Yiyi Zhou","Rongrong Ji","Xing Sun"],"abstract":"Establishing the long-context capability of large vision-language models is crucial for video understanding, high-resolution image understanding, multi-modal agents and reasoning. We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M tokens while delivering advanced performances on short-context multi-modal tasks. We propose an effective multi-modal training schema that starts with large language models and proceeds through vision-language alignment, general knowledge learning, and two sequential stages of long-sequence fine-tuning. We further implement context-parallelism distributed inference and logits-masked language modeling head to scale Long-VITA to infinitely long inputs of images and texts during model inference. Regarding training data, Long-VITA is built on a mix of $17$M samples from public datasets only and demonstrates the state-of-the-art performance on various multi-modal benchmarks, compared against recent cutting-edge models with internal data. Long-VITA is fully reproducible and supports both NPU and GPU platforms for training and testing. We hope Long-VITA can serve as a competitive baseline and offer valuable insights for the open-source community in advancing long-context multi-modal understanding.","url_abs":"https://arxiv.org/abs/2502.05177v1","url_pdf":"https://arxiv.org/pdf/2502.05177v1.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":"long-vita-scaling-large-multi-modal-models-to","repo_url":"https://github.com/vita-mllm/long-vita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.05177","atlas_url":"https://app.syntology.ai/?focus=2502.05177","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}