AINeutralarXiv – CS AI · 7h ago6/10
🧠
Variational Learning for Insertion-based Generation
Researchers introduce the Insertion Process (IP), a novel generative model that learns optimal insertion orders for variable-length sequence generation, moving beyond fixed-length masked diffusion approaches. The framework uses permutation-based variational inference to jointly optimize what, where, and when to insert tokens, demonstrating improvements in goal-conditioned planning and molecular generation tasks.