{"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/vita-1-5-towards-gpt-4o-level-real-time","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","arxiv_id":"2501.01957","date":"2025-01-03","proceeding":null,"authors":["Chaoyou Fu","Haojia Lin","Xiong Wang","Yi-Fan Zhang","Yunhang Shen","Xiaoyu Liu","Haoyu Cao","Zuwei Long","Heting Gao","Ke Li","Long Ma","Xiawu Zheng","Rongrong Ji","Xing Sun","Caifeng Shan","Ran He"],"abstract":"Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.","url_abs":"https://arxiv.org/abs/2501.01957v3","url_pdf":"https://arxiv.org/pdf/2501.01957v3.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":"vita-1-5-towards-gpt-4o-level-real-time","repo_url":"https://github.com/VITA-MLLM/VITA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.01957","atlas_url":"https://app.syntology.ai/?focus=2501.01957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.01957"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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://github.com/VITA-MLLM/VITA","reach":null}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"c4108604c4fe6c31","entry":"make_shared_position_ids","repo":"VITA-MLLM/VITA","repo_kind":"official","path":"vita/model/vita_arch.py","file_url":"https://github.com/VITA-MLLM/VITA/blob/HEAD/vita/model/vita_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c4108604c4fe6c31"}},{"code_sha256_prefix":"5364930589ac5880","entry":"merge_consecutive_tuples","repo":"VITA-MLLM/VITA","repo_kind":"official","path":"vita/model/vita_arch.py","file_url":"https://github.com/VITA-MLLM/VITA/blob/HEAD/vita/model/vita_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5364930589ac5880"}},{"code_sha256_prefix":"6bdb9c11584c789d","entry":"VITAMetaForCausalLM","repo":"VITA-MLLM/VITA","repo_kind":"official","path":"vita/model/vita_arch.py","file_url":"https://github.com/VITA-MLLM/VITA/blob/HEAD/vita/model/vita_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6bdb9c11584c789d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}