Delta Sampling: Data-Free Knowledge Transfer Across Diffusion Models

Recent advancements in diffusion models have led to the introduction of Refa\c{c}ade, a novel method for Object Retexture, which allows for the transfer of local textures from a reference object to a target object in images or videos. This method addresses the limitations of existing approaches by enhancing controllability and precision in texture transfer through innovative designs, including a texture remover trained on 3D mesh renderings.

A novel method called Dual LoRA has been proposed to enhance the performance of Low-Rank Adaptation (LoRA) in fine-tuning large language models (LLMs). This method introduces two distinct groups within low-rank matrices: a magnitude group for controlling the extent of parameter updates and a direction group for determining the update direction, thereby improving the adaptation process.

The introduction of NAS-LoRA represents a significant advancement in the adaptation of the Segment Anything Model (SAM) for specialized tasks, particularly in medical and agricultural imaging. This new Parameter-Efficient Fine-Tuning (PEFT) method integrates a Neural Architecture Search (NAS) block to enhance SAM's performance by addressing its limitations in acquiring high-level semantic information due to the lack of spatial priors in its Transformer encoder.

A recent study highlights the vulnerabilities of proactive defenses against deepfakes, revealing that these defenses often lack the necessary robustness and reliability. The research introduces a novel technique called Low-Rank Adaptation (LoRA) patching, which effectively bypasses existing defenses by injecting adaptable patches into deepfake generators. This method also includes a Multi-Modal Feature Alignment loss to ensure semantic consistency in outputs.

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.

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.

Recent advancements in diffusion models have led to the development of a phase-aware strategy that accelerates image generation by applying different speedups to various stages of the process. This approach utilizes lightweight LoRA adapters, named Slow-LoRA and Fast-LoRA, to enhance efficiency without extensive retraining of models.