TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917953991081984 |
|---|---|
| author | VanderHoeven, Hannah Bhalla, Brady Khebour, Ibrahim Youngren, Austin Venkatesha, Videep Bradford, Mariah Fitzgerald, Jack Mabrey, Carlos Tu, Jingxuan Zhu, Yifan Lai, Kenneth Jung, Changsoo Pustejovsky, James Krishnaswamy, Nikhil |
| author_facet | VanderHoeven, Hannah Bhalla, Brady Khebour, Ibrahim Youngren, Austin Venkatesha, Videep Bradford, Mariah Fitzgerald, Jack Mabrey, Carlos Tu, Jingxuan Zhu, Yifan Lai, Kenneth Jung, Changsoo Pustejovsky, James Krishnaswamy, Nikhil |
| contents | We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks. With a focus on fast, real-time performance, TRACE tracks the speech, actions, gestures, and visual attention of participants, uses these multimodal inputs to determine the set of task-relevant propositions that have been raised as the dialogue progresses, and tracks the group's epistemic position and beliefs toward them as the task unfolds. Amid increased interest in AI systems that can mediate collaborations, TRACE represents an important step forward for agents that can engage with multiparty, multimodal discourse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09511 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues VanderHoeven, Hannah Bhalla, Brady Khebour, Ibrahim Youngren, Austin Venkatesha, Videep Bradford, Mariah Fitzgerald, Jack Mabrey, Carlos Tu, Jingxuan Zhu, Yifan Lai, Kenneth Jung, Changsoo Pustejovsky, James Krishnaswamy, Nikhil Computation and Language We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks. With a focus on fast, real-time performance, TRACE tracks the speech, actions, gestures, and visual attention of participants, uses these multimodal inputs to determine the set of task-relevant propositions that have been raised as the dialogue progresses, and tracks the group's epistemic position and beliefs toward them as the task unfolds. Amid increased interest in AI systems that can mediate collaborations, TRACE represents an important step forward for agents that can engage with multiparty, multimodal discourse. |
| title | TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.09511 |