Related papers: NTK-Guided Implicit Neural Teaching

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

In solving partial differential equations (PDEs), machine learning utilizing physical laws has received considerable attention owing to advantages such as mesh-free solutions, unsupervised learning, and feasibility for solving…

Implicit Neural Representation (INR) has recently attracted considerable attention for storing various types of signals in continuous forms. The existing INR networks require lengthy training processes and high-performance computational…

The Neural Tangent Kernel (NTK) characterizes how a model's state evolves over Gradient Descent. Computing the full NTK matrix is often infeasible, especially for recurrent architectures. Here, we introduce a matrix-free perspective, using…

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are…

We present SegINR, a novel approach to neural Text-to-Speech (TTS) that addresses sequence alignment without relying on an auxiliary duration predictor and complex autoregressive (AR) or non-autoregressive (NAR) frame-level sequence…

Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking…

Time series data are often affected by various forms of corruption, such as missing values, noise, and outliers, which pose significant challenges for tasks such as forecasting and anomaly detection. To address these issues, inverse…

Physics-informed neural networks (PINNs) are promising to replace conventional partial differential equation (PDE) solvers by offering more accurate and flexible PDE solutions. However, they are hampered by the relatively slow convergence…

X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT…

In this paper, a novel multi-head multi-layer perceptron (MLP) structure is presented for implicit neural representation (INR). Since conventional rectified linear unit (ReLU) networks are shown to exhibit spectral bias towards learning…

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their…

In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial…

Neural implicit representations have become a popular choice for modeling surfaces due to their adaptability in resolution and support for complex topology. While previous works have achieved impressive reconstruction quality by training on…

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks…

Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applications such as interpolating new coordinates and signal…

Physics-informed neural networks (PINNs) have emerged as a promising numerical method based on deep learning for modeling boundary value problems, showcasing promising results in various fields. In this work, we use PINNs to discretize…

In suitably initialized wide networks, small learning rates transform deep neural networks (DNNs) into neural tangent kernel (NTK) machines, whose training dynamics is well-approximated by a linear weight expansion of the network at…

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the…