Product
New VAE method hits SOTA on MNIST by losing on purpose
OpenAI Blog · Jul 20, 2026 · 2 min read
The core tension in representation learning has always been about what to keep and what to throw away. A new paper prop...
Topic: variational-autoencoders
3 articles
Explore our coverage of variational-autoencoders — 3 curated articles, summaries, and related resources from the Inblix archive.
Product
Deep generative models learn to predict full robot trajectories, not just next steps
OpenAI Blog · Jul 20, 2026 · 2 min read
Robot learning has a long-standing problem: dynamics models that predict one timestep at a time fall apart over long ho...
Product
VAE-like option discovery VALOR unlocks 4x more robot skills
OpenAI Blog · Jul 19, 2026 · 2 min read
A new paper draws a direct line between variational autoencoders and how reinforcement learning agents discover reusabl...