Abstract The Hausdorff distance is a fundamental metric with widespread applications across various fields. However, its computation remains computationally expensive, especially for large‐scale datasets. This work targets exact point‐to‐point Hausdorff distance on point sets. In this work, we present RT‐HDIST, the first Hausdorff distance algorithm accelerated by ray‐tracing cores (RT‐cores). By reformulating the Hausdorff distance problem as a series of nearest‐neighbor searches and introducing a novel quantized voxel‐index space, RT‐HDIST achieves significant reductions in computational overhead while maintaining exact results. Extensive benchmarks demonstrate up to a two‐order‐of‐magnitude speedup over prior state‐of‐the‐art methods, underscoring RT‐HDIST's potential for real‐time and large‐scale applications.

Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech. However, an LLM-based strategy for modeling spoken dialogs remains elusive, calling for further investigation. This paper introduces an extensive speech-text LLM framework, the Unified Spoken Dialog Model (USDM), designed to generate coherent spoken responses with naturally occurring prosodic features relevant to the given input speech without relying on explicit automatic speech recognition (ASR) or text-to-speech (TTS) systems. We have verified the inclusion of prosody in speech tokens that predominantly contain semantic information and have used this foundation to construct a prosody-infused speech-text model. Additionally, we propose a generalized speech-text pretraining scheme that enhances the capture of cross-modal semantics. To construct USDM, we fine-tune our speech-text model on spoken dialog data using a multi-step spoken dialog template that stimulates the chain-of-reasoning capabilities exhibited by the underlying LLM. Automatic and human evaluations on the DailyTalk dataset demonstrate that our approach effectively generates natural-sounding spoken responses, surpassing previous and cascaded baselines. Our code and checkpoints are available at https://github.com/naver-ai/usdm.

In this article, we explore the advantages of heuristic mechanisms and devise a new optimization framework named sequential motion optimization (SMO) to strengthen gradient-based methods. The key idea of SMO is inspired from a movement mechanism in a recent metaheuristic method called balancing composite motion optimization (BCMO). Specifically, SMO establishes a sequential motion chain of two gradient-guided individuals, including a leader and a follower to enhance the effectiveness of parameter updates in each iteration. A surrogate gradient model with low computation cost is theoretically established to estimate the gradient of the follower by that of the leader through chain rule during the training process. Experimental results in terms of training quality on both fully connected multilayer perceptrons (MLPs) and convolutional neural networks (CNNs) with respect to three popular benchmark datasets, including MNIST, Fashion-MNIST, and CIFAR-10 demonstrate the superior performance of the proposed framework in comparison with the vanilla stochastic gradient descent (SGD) implemented via backpropagation (BP) algorithm. Although this study only introduces the vanilla gradient descent (GD) as a main gradient-guided factor in SMO for deep neural network (DNN) training application, it is great potential to combine with other gradient-based variants to improve its effectiveness and solve other large-scale optimization problems in practice.

Recently many researches have been studied to run autonomous flying vehicles. Especially, quadrotor VTOL (Vertical Take-Off and Landing) has been a challenging subject. To stabilize the quadrotor system, many control algorithms and sensor systems have been developed. Most of them are based on the sensors like accelerometer, gyroscope, or IMU (Inertial Measurement Unit) to measure the attitude of quadrotor. Instead of using these conventional sensors, we apply one vision sensor to stabilize the attitude of a quadrotor system. To achieve this, four laser diodes are evenly distributed in the bottom plane of quadrotor, and then they point downwards. The positions of projected laser markers depend on the attitude and height of the quadrotor. We develop a control algorithm to stabilize the attitude as well as to control the height of a quadrotor. We show that the visual tracking of the laser markers is sufficient to estimate the state of the quadrotor attitude and control the attitude into a desired state.