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

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

While filtered back projection (FBP) is still the method of choice for fast tomographic reconstruction, its performance degrades noticeably in the presence of noise, incomplete sampling, or non-standard scan geometries. We propose a…

Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and…

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

Neuro-fuzzy networks (NFNs) are transparent, symbolic, and universal function approximations that perform as well as conventional neural architectures, but their knowledge is expressed as linguistic IF-THEN rules. Despite these advantages,…

Multispectral and Hyperspectral Image Fusion (MHIF) aims to reconstruct high-resolution images by integrating low-resolution hyperspectral images (LRHSI) and high-resolution multispectral images (HRMSI). However, existing methods face…

Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different resource usage. However, its wide adoption is hindered by a fundamental conflict with the…

Few-Shot Class Incremental Learning (FSCIL) is crucial for adapting to the complex open-world environments. Contemporary prospective learning-based space construction methods struggle to balance old and new knowledge, as prototype bias and…

For better explore the relations of inter-modal and inner-modal, even in deep learning fusion framework, the concept of decomposition plays a crucial role. However, the previous decomposition strategies (base \& detail or low-frequency \&…

Learning-based optimal control algorithms control unknown systems using past trajectory data and a learned model of the system dynamics. These controllers use either a linear approximation of the learned dynamics, trading performance for…

Continual learning, the ability to acquire knowledge from new data while retaining previously learned information, is a fundamental challenge in machine learning. Various approaches, including memory replay, knowledge distillation, model…

We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generative trajectories for $N$ dimensional data by embedding paths…

Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of pre-trained models when deployed on resource-constrained…

Due to the complex interplay of light absorption and scattering in the underwater environment, underwater images experience significant degradation. This research presents a two-stage underwater image enhancement network called the…

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…

CLIP has revolutionized zero-shot learning by enabling task generalization without fine-tuning. While prompting techniques like CoOp and CoCoOp enhance CLIP's adaptability, their effectiveness in Federated Learning (FL) remains an open…

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting…

Nonnegative Matrix Factorization (NMF) is a versatile and powerful tool for discovering latent structures in data matrices, with many variations proposed in the literature. Recently, Leplat et al.\@ (2019) introduced a minimum-volume NMF…

Federated learning (FL) facilitates the secure utilization of decentralized images, advancing applications in medical image recognition and autonomous driving. However, conventional FL faces two critical challenges in real-world deployment:…