Industry
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Specifically, instead of directly measuring the divergence with paired images, we train a reward model with the dataset we construct, consisting of nearly 51,000 images annotated with human preferences.
Combating Bilateral Edge Noise for Robust Link Prediction
Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated.
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
The pursuit of realistic image synthesis at arbitrary views, given only a single source image, has long been a cornerstone challenge in computer vision and graphics.
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment Ben Usman
The variability of what "similar" means in this context, which transformations are allowed, and whether data points themselves or their feature representations
