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.
Subfield
Autoregressive and tokenizer-based generation
Benchmarks: ImageNet 256x256 generation (gFID), ImageNet reconstruction (rFID), UCF-101 class-conditional video generation, GenEval for autoregressive text-to-image. Datasets: ImageNet-1k, Open Images, UCF101, MS-COCO. Baselines: VQ-VAE, VQGAN, MaskGIT, FSQ and others.