3 stories
Variational autoencoders (VAEs) are a key part of modern text-to-image models, which generate images within their latent space. VAEs are known to disentangle the main factors of variation in the data, and color is known to be one of the most structured of these in natural images: decorrelating it…
Recent world action models (WAMs) reuse pretrained video VAEs whose encoder latents directly condition downstream action policies. Quantization must therefore preserve not only reconstruction fidelity but also the policy-facing latent contract expected by the frozen policy.
guest post with Dóra JámborThis is a half-guest-post written jointly with Dóra, a fellow participant in a reading group where we recently discussed the original paper on $\beta$-VAEs:Irina Higgins et al (ICLR 2017): $\beta$-VAE:
Showing 3 of 3 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
