#Diffusion models
Latest news articles tagged with "Diffusion models". Follow the timeline of events, related topics, and entities.
Articles (6)
-
🇺🇸 Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
[USA]
arXiv:2602.22570v1 Announce Type: cross Abstract: Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance ...
Related: #AI evaluation methodology, #Computer vision -
🇺🇸 LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration
[USA]
arXiv:2602.20497v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transform...
Related: #AI acceleration, #Computer vision -
🇺🇸 B-DENSE: Branching For Dense Ensemble Network Learning
[USA]
arXiv:2602.15971v1 Announce Type: cross Abstract: Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterat...
Related: #Generative modeling, #Inference acceleration, #Model distillation, #Dense ensemble learning -
🇺🇸 Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models
[USA]
arXiv:2602.16634v1 Announce Type: cross Abstract: The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently...
Related: #Molecular dynamics, #Rare-event sampling, #Free‑energy calculations, #Biomolecular simulation -
🇺🇸 Fast and Scalable Analytical Diffusion
[USA]
arXiv:2602.16498v1 Announce Type: cross Abstract: Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes p...
Related: #Generative modeling, #Scalability challenges, #Empirical Bayes methods, #Machine learning research -
🇺🇸 Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
[USA]
arXiv:2602.12393v1 Announce Type: cross Abstract: DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging sele...
Related: #AI image editing, #Reproducibility research, #Interactive technology