ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
This addresses the problem of enhancing human-AI interactivity for users of MLLMs, offering a more flexible and seamless experience, though it appears incremental as it builds on existing MLLM frameworks.
The paper tackles the limitation of multimodal large language models (MLLMs) in interactive accuracy and efficiency by introducing precise referring instructions using points and boxes, and proposes ChatSpot, a unified model that supports diverse forms like mouse clicks and drag-and-drop, achieving promising performance in evaluation tasks.
Human-AI interactivity is a critical aspect that reflects the usability of multimodal large language models (MLLMs). However, existing end-to-end MLLMs only allow users to interact with them through language instructions, leading to the limitation of the interactive accuracy and efficiency. In this study, we present precise referring instructions that utilize diverse reference representations such as points and boxes as referring prompts to refer to the special region. This enables MLLMs to focus on the region of interest and achieve finer-grained interaction. Based on precise referring instruction, we propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes, which provides a more flexible and seamless interactive experience. We also construct a multi-grained vision-language instruction-following dataset based on existing datasets and GPT-4 generating. Furthermore, we design a series of evaluation tasks to assess the effectiveness of region recognition and interaction. Experimental results showcase ChatSpot's promising performance.