Related papers: Null-Space Filtering for Data-Free Continual Model…

In this paper, we propose a learning-based framework for non-rigid shape registration without correspondence supervision. Traditional shape registration techniques typically rely on correspondences induced by extrinsic proximity, therefore…

Generalizing neural surrogate models across different PDE parameters remains difficult because changes in PDE coefficients often make learning harder and optimization less stable. The problem becomes even more severe when the model must…

Recently,vision-based robotic manipulation has garnered significant attention and witnessed substantial advancements. 2D image-based and 3D point cloud-based policy learning represent two predominant paradigms in the field, with recent…

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature…

The UNet-enhanced Fourier Neural Operator (UFNO) extends the Fourier Neural Operator (FNO) by incorporating a parallel UNet pathway, enabling the retention of both high- and low-frequency components. While UFNO improves predictive accuracy…

Machine fault diagnosis (FD) is a critical task for predictive maintenance, enabling early fault detection and preventing unexpected failures. Despite its importance, existing FD models are operation-specific with limited generalization…

Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility by selectively activating task-relevant parameters and efficiently composing experts across…

There is a growing interest in developing data-driven reduced-order models for atmospheric and oceanic flows that are trained on data obtained either from high-resolution simulations or satellite observations. The data-driven models are…

In this paper, we propose a novel learning-based framework for 3D shape registration, which overcomes the challenges of significant non-rigid deformation and partiality undergoing among input shapes, and, remarkably, requires no…

Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress. However, state-of-art methods typically provide poor cross-scene generalization, and generated masked areas often…

In the rapidly evolving field of deep learning, specialized models have driven significant advancements in tasks such as computer vision and natural language processing. However, this specialization leads to a fragmented ecosystem where…

Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these models remain fundamentally limited in spatially-aware tasks…

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major…

Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal…

Multi-modal image fusion aims to integrate complementary information from multiple source images to produce high-quality fused images with enriched content. Although existing approaches based on state space model have achieved satisfied…

Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models…

Functional data, representing curves or trajectories, are ubiquitous in fields like biomedicine and motion analysis. A fundamental challenge is phase variability -- temporal misalignments that obscure underlying patterns and degrade model…

Current multispectral object detection methods often retain extraneous background or noise during feature fusion, limiting perceptual performance. To address this, we propose an innovative feature fusion framework based on cross-modal…

Digital twins (DTs) rely on continuous synchronization between physical systems and their virtual counterparts through online parameter estimation under uncertainty. In many practical settings, however, this task is challenged by low…

Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representational divergence arising from permutation invariance, random initialization, and heterogeneous…