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.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
Anomaly Preference Optimization reformulates anomaly image generation as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module in diffusion models.
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.
citing papers explorer
-
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.
-
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
Threshold-Guided Optimization for Visual Generative Models
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
-
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module in diffusion models.
-
On the Robustness of Distribution Support under Diffusion Guidance
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.