From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Covers training a 3-billion-parameter state-space vision model from scratch to state-of-the-art. Teaches methods for efficient large-model training and architectural choices for vision tasks.

A 21-minute video from AI Engineer: “From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam”.

Video by AI Engineer, played through YouTube's embedded player.