JevRec uses variable-length item codes for generative recommendation
On three public datasets it beat compared baselines and used less train and inference time than TIGER.
2 stories, newest first · one card per story
On three public datasets it beat compared baselines and used less train and inference time than TIGER.
On NQ320K, jointly evolving SID construction and collision handling lifts Recall@1 from 55.8% to 59.3%.
Today 949 readers · 1.3K views · 1K reads · all time 159K views