Introduces the Insertion Process model for variable-length non-monotonic sequence generation via a bijective permutation mapping and permutation-based variational inference.
Genmol: A drug discovery generalist with discrete diffusion
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 9representative citing papers
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
FORGE reformulates molecular optimization as context-aware fragment ranking and replacement using mined low-to-high edit pairs, outperforming larger language models and graph methods on standard benchmarks.
SCMDM is a post-training self-conditioning adaptation for masked diffusion models that reduces generative perplexity by nearly 50% on OWT and improves performance on images, molecules, and genomics.
A diffusion language model over fragment strings, refined by an ICEBERG forward spectral simulator, achieves state-of-the-art de novo molecular identification from tandem mass spectra.
BlockGen enables flexible blockwise diffusion modeling with mixed block sizes and ARPC sampling, finding uniform diffusion outperforms masked under ancestral sampling in few-step regimes while the gap reverses with ARPC at high NFE.
PhAME introduces compositional classifier-free guidance in a latent diffusion model for phenotype-aware molecular editing, claiming SOTA performance on docking and phenotypic benchmarks.
SGRPO is a GRPO-style framework that constructs set-level diversity rewards via supergroup sampling and leave-one-out redistribution to expand the utility-diversity Pareto frontier in biomolecular design tasks.
Generative chemical language models pretrained on general chemical data and fine-tuned on energetic materials datasets enable accelerated discovery of synthetically accessible high-performance compounds.
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.
-
Adaptive Order Policies for Masked Diffusion
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
-
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
FORGE reformulates molecular optimization as context-aware fragment ranking and replacement using mined low-to-high edit pairs, outperforming larger language models and graph methods on standard benchmarks.
-
Simple Self-Conditioning Adaptation for Masked Diffusion Models
SCMDM is a post-training self-conditioning adaptation for masked diffusion models that reduces generative perplexity by nearly 50% on OWT and improves performance on images, molecules, and genomics.
-
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
A diffusion language model over fragment strings, refined by an ICEBERG forward spectral simulator, achieves state-of-the-art de novo molecular identification from tandem mass spectra.
-
BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
BlockGen enables flexible blockwise diffusion modeling with mixed block sizes and ARPC sampling, finding uniform diffusion outperforms masked under ancestral sampling in few-step regimes while the gap reverses with ARPC at high NFE.
-
PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion
PhAME introduces compositional classifier-free guidance in a latent diffusion model for phenotype-aware molecular editing, claiming SOTA performance on docking and phenotypic benchmarks.
-
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
SGRPO is a GRPO-style framework that constructs set-level diversity rewards via supergroup sampling and leave-one-out redistribution to expand the utility-diversity Pareto frontier in biomolecular design tasks.
-
Generative Chemical Language Models for Energetic Materials Discovery
Generative chemical language models pretrained on general chemical data and fine-tuned on energetic materials datasets enable accelerated discovery of synthetically accessible high-performance compounds.