GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

Junho Kim, Xu Cao, Houze Yang, Bikram Boote, Ana Jojic, Fiona Ryan, Bolin Lai, Sangmin Lee, James M. Rehg

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions: 2 upvotes on Hugging Face Daily Papers, #41 of 49 papers on 2026-05-19. Day-by-day upvote history.

Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to identify who interacts with whom in multi-person videos. We introduce GRASP, a large-scale social reasoning dataset that connects high-level social QA with fine-grained gaze and deictic gesture events. GRASP contains 290K question--answer pairs over 46K videos totaling 749 hours, organized by a 16-category taxonomy spanning gaze, gesture, and joint gaze--gesture reasoning, together with GRASP-Bench for evaluation. Unlike prior resources that focus on either isolated cues or high-level social QA, GRASP builds questions from identity-consistent gaze trajectories, deictic gestures, and their joint compositions into social events. Moreover, we propose Social Grounding Reward (SGR), a learning signal that uses these social events to encourage models to reason about the participants involved in each interaction. Experiments show that SGR improves performance on GRASP-Bench while maintaining zero-shot performance on related social video QA benchmarks.

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.