SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation

A new study introduces LineAR, a training-free progressive key-value cache compression pipeline designed to enhance autoregressive image generation by managing cache at the line level. This method effectively reduces memory bottlenecks associated with traditional autoregressive models, which require extensive storage for previously generated visual tokens during decoding.

A new study introduces BlackCAtt, a black-box algorithm designed to create explainable and imperceptible adversarial attacks on object detectors. This method utilizes minimal, causally sufficient pixel sets combined with bounding boxes to manipulate object detection outcomes without needing specific architecture knowledge.

Delta Sampling (DS) has been introduced as a novel method for enabling data-free knowledge transfer across different diffusion models, particularly addressing the challenges faced when upgrading base models like Stable Diffusion. This method operates at inference time, utilizing the delta between model predictions before and after adaptation, thus facilitating the reuse of adaptation components across varying architectures.

A recent thesis presents significant advancements in generative models, particularly focusing on normalizing flows and their applications in computer vision. Key innovations include the development of invertible convolution layers and efficient algorithms for training and inversion, enhancing the performance of these models in real-world scenarios.

Recent advancements in human preference optimization have been applied to text-to-image Diffusion Models, enhancing prompt alignment and visual appeal. The proposed method fine-tunes models like Stable Diffusion 1.5 and XL using perceptual objectives in the U-Net embedding space, significantly improving training efficiency and user preference alignment.