{"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/anymal-an-efficient-and-scalable-any-modality","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","arxiv_id":"2309.16058","date":"2023-09-27","proceeding":null,"authors":["Seungwhan Moon","Andrea Madotto","Zhaojiang Lin","Tushar Nagarajan","Matt Smith","Shashank Jain","Chun-Fu Yeh","Prakash Murugesan","Peyman Heidari","Yue Liu","Kavya Srinet","Babak Damavandi","Anuj Kumar"],"abstract":"We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful text-based reasoning abilities of the state-of-the-art LLMs including LLaMA-2 (70B), and converts modality-specific signals to the joint textual space through a pre-trained aligner module. To further strengthen the multimodal LLM's capabilities, we fine-tune the model with a multimodal instruction set manually collected to cover diverse topics and tasks beyond simple QAs. We conduct comprehensive empirical analysis comprising both human and automatic evaluations, and demonstrate state-of-the-art performance on various multimodal tasks.","url_abs":"https://arxiv.org/abs/2309.16058v1","url_pdf":"https://arxiv.org/pdf/2309.16058v1.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":"anymal-an-efficient-and-scalable-any-modality","repo_url":"https://github.com/nokia-bell-labs/papagei-foundation-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-situated","task":"Video Question Answering","dataset":"STAR Benchmark","model":"AnyMAL-70B (0-shot)","rank_in_archive_order":9,"of":17,"metrics":{"Average Accuracy":"48.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2309.16058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}