PhD researcher launches 'paper nostalgia' series with Real NVP coupling-layer explainer
LucaAmb · x · 2026-11-05
A researcher has started a "paper nostalgia" series revisiting the classic papers that shaped their PhD, with original illustrated threads.
- Episode #2 covers "Density estimation using Real NVP" (Dinh et al., ICLR 2017), framed as an intro to coupling layers: the figure shows the invertible mapping between data space and latent space — inference via z=f(x) turns a two-moons distribution into a Gaussian, generation via x=f⁻¹(z) reverses it.
- Episode #1 revisited "Your Classifier is Secretly an Energy Based Model" by Will Grathwohl et al. (ICLR 2020).
More from Research
- HyperQ adds trainable quantum residual branches to a frozen 1.1B diffusion LM — jiqizhixin · 2026-11-05
- Open-source PageIndex ditches vectors for tree-search RAG, scores 98.7% on FinanceBench vs GPT-4o's 31% — aakashgupta · 2026-11-05
- Andriy Burkov releases 'The Hundred-Page Language Models Book', a hands-on PyTorch guide — burkov · 2026-11-05
- Blogger proposes scrapping ML conference checklists now that everyone uses LLMs to vet papers — bremen79 · 2026-11-05
- Agent harnesses aren't dying: harness distillation changes the job, says O'Reilly — bibryam · 2026-11-05
- VAMOS hierarchical VLA lets a robot self-navigate 2.35 km through Zurich — KyleMorgenstein · 2026-11-05