Eimran Eimon Presents His Research on Split Inference at AAAS Annual Meeting 2026

At the Annual Meeting of the American Association for the Advancement of Science (AAAS), one of the world’s most distinguished scientific gatherings, Eimran Eimon presented his research on split inference and Feature Coding for Machines to an international audience of scientists, engineers, and policy leaders.

His presentation explained how Feature Coding for Machines, an emerging next generation standard, enables the transmission of compact neural intermediate features rather than original video streams. By shifting machine-to-machine communication from pixels to features, this approach supports scalable, bandwidth efficient, and privacy preserving deployment of distributed visual AI across smart cities, intelligent transportation systems, public safety networks, and autonomous platforms.