One Latent Space to Rule All Degradations: Unifying Restoration Knowledge for Image Fusion

This paper introduces a novel approach to self pre-training using topology- and spatiality-aware Masked Autoencoders (MAEs) for 3D medical image segmentation. The proposed method enhances the ability of Vision Transformers (ViTs) to capture geometric shape and spatial information, which are crucial for accurate segmentation. A new topological loss is introduced to preserve geometric shape information, improving the performance of MAEs in medical imaging tasks.

EBind is a novel approach to space binding that simplifies the process by utilizing a single encoder per modality and high-quality data. This method allows for the training of state-of-the-art models on a single GPU within hours, significantly reducing the time compared to traditional methods. EBind employs a dataset comprising 6.7 million automated multimodal quintuples, 1 million semi-automated triples, and 3.4 million captioned data items, demonstrating superior performance with a 1.8 billion parameter model.

The paper presents PIP (Perturbation-based Iterative Pruning), a new method designed to optimize Large Language Models (LLMs) by reducing their parameter count while maintaining accuracy. PIP employs a double-view structured pruning approach, utilizing both unperturbed and perturbed views to identify and prune parameters that do not significantly contribute to model performance. Experimental results indicate that PIP can decrease the parameter count by around 20% while preserving over 85% of the original model's accuracy across various benchmarks.

Recent advancements in learning-based methods have significantly reduced the computational complexity associated with traditional trajectory similarity computation. However, current state-of-the-art methods do not fully utilize the extensive range of trajectory information for effective similarity modeling. To address this issue, a novel method named RePo has been proposed. This method jointly encodes region-wise and point-wise features to effectively capture both spatial context and detailed moving patterns. The approach involves mapping GPS trajectories to grid sequences and utilizing lightw…