A new arXiv paper explores multimodal rapport estimation in real-world Human-Robot Interaction (HRI) settings, moving beyond controlled lab environments. Researchers found that zero-shot Large Language Models (LLMs) performed well, with Gemini 2.5-Flash showing particular strength. A fusion model combining Gemini's text capabilities with audio (HuBERT) and visual (V-JEPA) models achieved the best overall performance, suggesting that a combination of modalities is crucial for accurate rapport estimation in dynamic, real-world scenarios. AI
IMPACT This research could lead to more adaptive and responsive robots in real-world interactions by improving their ability to gauge user engagement.
RANK_REASON The cluster contains an academic paper published on arXiv detailing new research findings. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
