Anymal: An Efficient And Scalable Any-modality Augmented Language Model

Moon Seungwhan, Madotto Andrea, Lin Zhaojiang, Nagarajan Tushar, Smith Matt, Jain Shashank, Yeh Chun-fu, Murugesan Prakash, Heidari Peyman, Liu Yue, Srinet Kavya, Damavandi Babak, Kumar Anuj. Arxiv 2023

[Paper]    
Multimodal Models

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.

Similar Work