Related papers: Tabulated MLP for Fast Point Feature Embedding

Ophthalmic image segmentation serves as a critical foundation for ocular disease diagnosis. Although fully convolutional neural networks (CNNs) are commonly employed for segmentation, they are constrained by inductive biases and face…

Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these…

The goal of mechanistic interpretability is discovering simpler, low-rank algorithms implemented by models. While we can compress activations into features, compressing nonlinear feature-maps -- like MLP layers -- is an open problem. In…

Joint object matching, also known as multi-image matching, namely, the problem of finding consistent partial maps among all pairs of objects within a collection, is a crucial task in many areas of computer vision. This problem subsumes…

Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…

Multiple patterning lithography (MPL) is regarded as one of the most promising ways of overcoming the resolution limitations of conventional optical lithography due to the delay of next-generation lithography technology. As the feature size…

Accurate prediction of surface energies and stabilities is essential for materials design, yet first-principles calculations remain computationally expensive and most existing interatomic potentials are trained only on bulk systems. Here,…

We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings. End-to-end optimization of positional embedding parameters along with network weights leads to poor generalization…

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

Point cloud classification plays a crucial role in the processing and analysis of data from 3D sensors such as LiDAR, which are commonly used in applications like autonomous vehicles, robotics, and environmental monitoring. However,…

There is an increasing interest in the application of deep learning architectures to tabular data. One of the state-of-the-art solutions is TabTransformer which incorporates an attention mechanism to better track relationships between…

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…

In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both…

Lidars and cameras play essential roles in autonomous driving, offering complementary information for 3D detection. The state-of-the-art fusion methods integrate them at the feature level, but they mostly rely on the learned soft…

In order to achieve better performance for point cloud analysis, many researchers apply deeper neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over irregular point cloud. However, applying dense MLP convolutions over…

Look-Up Table based methods have emerged as a promising direction for efficient image restoration tasks. Recent LUT-based methods focus on improving their performance by expanding the receptive field. However, they inevitably introduce…

SymPoint is an initial attempt that utilizes point set representation to solve the panoptic symbol spotting task on CAD drawing. Despite its considerable success, it overlooks graphical layer information and suffers from prohibitively slow…

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

Machine learning potentials (MLPs) for atomistic simulations have an enormous prospective impact on materials modeling, offering orders of magnitude speedup over density functional theory (DFT) calculations without appreciably sacrificing…