Students Professional
JA EN

#end-to-end

2 articles

01 ·★ MEMBER·PAPER·10 min read Paper Explained — GenFirst: Let Generation Shape the Latent Space First, Reconstruction Second Image generation normally means training a VAE first and bolting a generative model onto its frozen latent space. This paper trains both at once without latent collapse — the key is the entropy term inside the KL objective, plus a simple rule: let generation go first and ramp reconstruction up later. 02 ·Agents·★ MEMBER·PAPER·9 min read End-to-End Driving from Scratch — Perception to Control in a Single Network End-to-end autonomous driving learns everything from camera pixels to steering in one neural network. Starting from zero, we cover how it differs from the modular stack, imitation learning and distribution shift, why 'predicting the average' causes crashes, and why interpretability and validation remain the hard part.