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
Algorithmic reasoning, length generalisation and program synthesis
Benchmarks: CLRS-30, CLRS-Text, ARC-AGI, ARC-AGI-2 and others. Datasets: CLRS-30 trajectories, ARC-AGI tasks, APPS, Modular arithmetic (grokking) tables. Baselines: Triplet-GMPNN, Pointer Graph Networks, Neural execution of graph algorithms, Relational Transformer and others.