Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Generative models
Generative modelling research builds models that sample images, audio and other signals: diffusion and flow matching, autoregressive models over learned tokens, and audio/speech generation, together with the metrics used to judge them. Results are reported as distribution-level scores (FID and relatives) on fixed reference sets, prompt-following benchmarks and human preference studies, at a stated sampling cost.