The Amazon seeks research proposals focused on advancing on-device multimodal perception, including generative visual experience, efficient visual encoding, and learned sensor fusion for object tracking. Proposals are welcomed in three main research areas: generative visual experience beyond capture constraints, efficient visual encoding for on-device vision-language models, and learned multimodal sensor fusion for object tracking. Each
Access Restricted: Members-Only Content. We're sorry, but this content is available exclusively to our subscribed members:
