mRNAutilus generates full-length therapeutic mRNAs via diffusion models and multi-objective guidance, achieving over 400-fold expression gains for luciferase and outperforming baselines for Spike and other targets in zero-shot tests.
arXiv preprint arXiv:2509.25171 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
GeoCycler aligns latent diffusion models via reward-weighted training with a type-gated stair reward to raise cyclic peptide closure rates across multiple topologies on the LNR benchmark.
A2D2 derives the Radon-Nikodym derivative for joint insertion-unmasking paths in discrete diffusion to enable reward-tilted fine-tuning and introduces the Adaptive Joint Decoding loss.
AlloGen decouples backbone generation from an SE(3)-invariant graph transformer scorer trained with curriculum learning to produce conformation-selective binders, with experimental validation on calmodulin showing holo-specific peptides.
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
citing papers explorer
-
mRNAutilus: Multi-Objective-Guided Discrete Generation of mRNA with Optimized Therapeutic Properties
mRNAutilus generates full-length therapeutic mRNAs via diffusion models and multi-objective guidance, achieving over 400-fold expression gains for luciferase and outperforming baselines for Spike and other targets in zero-shot tests.
-
GeoCycler: Reward-Aligned 3D Diffusion for Constraint-Conditioned Cyclic Peptide Design
GeoCycler aligns latent diffusion models via reward-weighted training with a type-gated stair reward to raise cyclic peptide closure rates across multiple topologies on the LNR benchmark.
-
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding
A2D2 derives the Radon-Nikodym derivative for joint insertion-unmasking paths in discrete diffusion to enable reward-tilted fine-tuning and introduces the Adaptive Joint Decoding loss.
-
AlloGen: Conformation-Selective Binder Generation with Differential State Scoring
AlloGen decouples backbone generation from an SE(3)-invariant graph transformer scorer trained with curriculum learning to produce conformation-selective binders, with experimental validation on calmodulin showing holo-specific peptides.
-
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.