Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge

Young-Jun Lee, dokyong, junyoung youn, Kyeongjin Oh, Byungsoo Ko, Jonghwan Hyeon, Ho-Jin Choi

Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge: 20 upvotes on Hugging Face Daily Papers, #7 of 15 papers on 2024-07-08. Day-by-day upvote history.

Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce Stark, a large-scale long-term multi-modal conversation dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct Stark automatically, we propose a novel multi-modal contextualization framework, Mcu, that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed Plan-and-Execute image aligner. Using our Stark, we train a multi-modal conversation model, Ultron 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. We make our source code and dataset publicly available.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.