Out-of-the-box: Black-box Causal Attacks on Object Detectors

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.

The introduction of SDPose marks a significant advancement in human pose estimation by leveraging pre-trained diffusion models, specifically Stable Diffusion, to enhance the accuracy and robustness of keypoint predictions in various contexts. This framework directly predicts keypoint heatmaps in the latent space of the SD U-Net, preserving generative priors and avoiding modifications that could disrupt the model's performance.