2025
Grounding Task Assistance with Multimodal Cues from a Single Demonstration
Gabriel Herbert Sarch, Balasaravanan Thoravi Kumaravel, Sahithya Ravi, Vibhav Vineet, Andrew D Wilson
ACL 2025finding
A person’s demonstration often serves as a key reference for others learning the same task. However, RGB video, the dominant medium for representing these demonstrations, often fails to capture fine-grained contextual cues such as intent, safety-critical environmental factors, and subtle preferences…