World Congress 2026 North America • Sep 26, 2026 • Session details

Point. Ask. Answer. Building Vision into AI on Constrained Hardware

Kavya Sri Chennoju

Build a privacy-first smart camera that processes visual data entirely on the edge. Discover how to deploy a 4-billion-parameter vision-language model locally on an 8GB Raspberry Pi.

Starting at 2:05 · Watch from the beginning

Point. Ask. Answer. Building Vision into AI on Constrained Hardware thumbnail

Checking access…

Playback and chapters load privately for Free videos.

Matching moments

7:00 min

Evaluating on-device data privacy, model performance, and cross-platform alternatives

Milan Todorovic · World Congress 2021

3:58 min

Controlling hardware cameras and analyzing visual frames

Marc Rousavy Marc Rousavy · World Congress 2025

51 sec

Overcoming inefficiencies in computer vision modeling

Antonio Tavera Antonio Tavera · World Congress 2025

4:08 min

Enabling edge intelligence with small language models

Sasha Denisov Sasha Denisov +1 · World Congress 2026 Europe

2:12 min

Distilling cloud AI capabilities into local device models

3:37 min

Hardware evolution from local inference to physical artificial intelligence

Vini Senger Vini Senger · World Congress 2026 North America

Upcoming sessions on this topic

Starts in 9 days

Conference India 2026

November 25–26, 2026

Bengaluru, India