Related papers: Continuous formulations and analytical properties …

In this paper, we introduce LGTM, a novel Local-to-Global pipeline for Text-to-Motion generation. LGTM utilizes a diffusion-based architecture and aims to address the challenge of accurately translating textual descriptions into…

The financial domain presents a complex environment for stock market prediction, characterized by volatile patterns and the influence of multifaceted data sources. Traditional models have leveraged either Convolutional Neural Networks (CNN)…

Many advances in Natural Language Processing have been based upon more expressive models for how inputs interact with the context in which they occur. Recurrent networks, which have enjoyed a modicum of success, still lack the…

Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable generation (consistent outputs) and valid generation…

Time series prediction can be generalized as a process that extracts useful information from historical records and then determines future values. Learning long-range dependencies that are embedded in time series is often an obstacle for…

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large…

The methodology named LIFE (Linear-in-Flux-Expressions) was developed with the purpose of simulating and analyzing large metabolic systems. With LIFE, the number of model parameters is reduced by accounting for correlations among the…

Moving and fixed bottlenecks are moving or fixed capacity restrictions that affect the propagation of traffic flow. They are a very important modeling approach to describe the effects of slow vehicles and traffic signals in transportation…

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Precise and timely traffic flow prediction plays a critical role in developing intelligent transportation systems and has attracted considerable attention in recent decades. Despite the significant progress in this area brought by deep…

This paper establishes a nonlinear separation principle based on contraction theory and derives sharp stability conditions for recurrent neural networks (RNNs). First, we introduce a nonlinear separation principle that guarantees global…

Graphs are fundamental tools for modeling pairwise interactions in complex systems. However, many real-world systems involve multi-way interactions that cannot be fully captured by standard graphs. Hypergraphs, which generalize graphs by…

Autonomous prediction of traffic demand will be a key function in future cellular networks. In the past, researchers have used statistical methods such as Autoregressive integrated moving average (ARIMA) to provide traffic predictions.…

This work outlines a Lattice Boltzmann Method (LBM) for geometrically and constitutively nonlinear solid mechanics to simulate large deformations under dynamic loading conditions. The method utilizes the moment chain approach, where the…

Optimization using network traffic models requires computing gradients of objective functions with respect to model parameters. However, derivation of such gradients has often been considered difficult or impractical due to their complexity…

Machine learning (ML) powered network traffic analysis has been widely used for the purpose of threat detection. Unfortunately, their generalization across different tasks and unseen data is very limited. Large language models (LLMs), known…

Nowadays, traffic management has become a challenge for urban areas, which are covering larger geographic spaces and facing the generation of different kinds of traffic data. This article presents a robust traffic estimation framework for…

Large Language Models (LLMs) have demonstrated extraordinary performance across a broad array of applications, from traditional language processing tasks to interpreting structured sequences like time-series data. Yet, their effectiveness…

The kinematic wave theory, originally proposed by (Lighthill and Whitham, 1955b; Richards, 1956), has been a good candidate for studying vehicular traffic. In this dissertation, we study kinematic wave models of network traffic, which are…

Distributed Machine Learning (DML) systems are utilized to enhance the speed of model training in data centers (DCs) and edge nodes. The Parameter Server (PS) communication architecture is commonly employed, but it faces severe long-tail…