mlsanityData to 7 Oct 2026

TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues

arXiv 2503.09511 ↗First posted 12 Mar 2025cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 14 of its 58 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

14 of 58 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  5. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  6. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  7. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  8. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  9. 2020The AVA-Kinetics Localized Human Actions Video Datasetcited by 82
  10. 2021DeliData: A dataset for deliberation in multi-party problem solvingcited by 26
  11. 2018Multimodal Grounding for Language Processingcited by 14
  12. 2024Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialoguescited by 6
2 more
  1. 2020A Formal Analysis of Multimodal Referring Strategies Under Common Groundcited by 5
  2. 2024Speech Is Not Enough: Interpreting Nonverbal Indicators of Common Knowledge and Engagementcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025Frictional Agent Alignment Framework: Slow Down and Don't Break Thingscited by 10
  2. 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomescited by 6
  3. 2025Dynamic Epistemic Friction in Dialoguecited by 4
  4. 2025Learning "Partner-Aware" Collaborators in Multi-Party Collaborationcited by 2
  5. 2026Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetrycited by 1
  6. 2025Computer Vision for Objects used in Group Work: Challenges and Opportunitiescited by 0
  7. 2026Unified Agent: Managing Interactions across Devicescited by 0
  8. 2026Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialoguecited by 0
  9. 2026Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignmentcited by 0