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
Vision-language models
Benchmarks: Zero-shot classification and retrieval (CLIP benchmark), COCO Captions retrieval, VQAv2, GQA and others. Datasets: LAION-5B, Conceptual Captions (CC3M), CC12M, COCO Captions and others. Baselines: CLIP, OpenCLIP, SigLIP 2, BLIP-2 and others.