Introduces the Insertion Process model for variable-length non-monotonic sequence generation via a bijective permutation mapping and permutation-based variational inference.
Malliaros, and Christopher Morris
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5verdicts
UNVERDICTED 5representative citing papers
IDDM interpolates diffusion transitions with a resampling mechanism to lessen dependence on intermediate latents and improve sample quality over masked and uniform discrete diffusion models.
EQUIMF is a unified equivariant framework that jointly generates discrete topologies and continuous geometries in molecular graphs via synchronized MeanFlow dynamics for efficient few-step sampling.
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.
Lightweight autoregressive graph generation model uses structure-guided ordering for efficient serialization and two-phase training to boost novelty while maintaining validity.
citing papers explorer
-
Variational Learning for Insertion-based Generation
Introduces the Insertion Process model for variable-length non-monotonic sequence generation via a bijective permutation mapping and permutation-based variational inference.
-
Interpolating Discrete Diffusion Models with Controllable Resampling
IDDM interpolates diffusion transitions with a resampling mechanism to lessen dependence on intermediate latents and improve sample quality over masked and uniform discrete diffusion models.
-
Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation
EQUIMF is a unified equivariant framework that jointly generates discrete topologies and continuous geometries in molecular graphs via synchronized MeanFlow dynamics for efficient few-step sampling.
-
Discrete Bayesian Sample Inference for Graph Generation
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.
-
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Lightweight autoregressive graph generation model uses structure-guided ordering for efficient serialization and two-phase training to boost novelty while maintaining validity.