Picture for Jiahao Nick Li

Jiahao Nick Li

OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

Add code
Sep 12, 2024
Figure 1 for OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Figure 2 for OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Figure 3 for OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Figure 4 for OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Viaarxiv icon

RoCap: A Robotic Data Collection Pipeline for the Pose Estimation of Appearance-Changing Objects

Add code
Jul 10, 2024
Viaarxiv icon

OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs

Add code
May 06, 2024
Viaarxiv icon