On-Device Multimodal Perception call for proposals - Fall 2026
On-Device Multimodal Perception call for proposals - Fall 2026 supports researchers advancing visual generation, efficient encoding, and sensor fusion to turn limited device captures into useful experiences and tracking.
Funder: Amazon Research Awards
Due Dates: October 1, 2026 (Submissions open) | November 4, 2026, 11:59 PM Pacific Time (Submission deadline)
Funding Amounts: No more than $80,000 USD in unrestricted funds and $40,000 USD in AWS Promotional Credits on average; one-year award period
Summary: Supports research on visual generation, efficient visual encoding, and sensor fusion that turns limited device captures into useful experiences and object tracking.
Key Information: Each PI may submit only one proposal per ARA call period; proposals must contain no confidential information.
Description
Amazon Research Awards, through Amazon’s Devices and Services organization, supports research bridging the gap between what compact devices capture and what users need. The call focuses on learned on-device processing and generative methods that turn limited observations into useful images, video, model-ready representations, or reliable estimates of object position and motion. Research should address real device limitations, including small sensors, modest optics, low-power hardware, and fixed power and thermal budgets.
The call welcomes theoretical advances, creative ideas, and practical applications across three topics: generating intended visual experiences beyond capture constraints, efficiently encoding visual input for on-device vision-language models, and learned multimodal sensor fusion for object tracking. Proposals may address multiple topics, with attention to evaluation and credible performance under relevant constraints.
