Related papers: Stop talking to me -- a communication-avoiding ADE…
This paper aims to accelerate decentralized optimization by strategically designing the edge weights used in the agent-to-agent message exchanges. We propose a Dynamic Directed Decentralized Gradient (D3GD) framework and show that the…
In this paper, we consider hybrid parallelism -- a paradigm that employs both Data Parallelism (DP) and Model Parallelism (MP) -- to scale distributed training of large recommendation models. We propose a compression framework called…
We study in this paper three variants of the high-order Discontinuous Galerkin (DG) method with Runge-Kutta (RK) time integration for the induction equation, analysing their ability to preserve the divergence free constraint of the magnetic…
Recently, adaptive control systems with relaxed persistent excitation (PE) conditions have been proposed to guarantee true parameter convergence and improve the transient response. However, in some cases, sufficient control performance and…
In this paper, we demonstrate that the explicit ADER approach as it is used inter alia in [1] can be seen as a special interpretation of the deferred correction (DeC) method as introduced in [2]. By using this fact, we are able to embed…
Residential demand response depends on sustained prosumer participation, yet existing coordination is either fully automated, or limited to one-way dispatch signals and price alerts that offer little possibility for informed…
This paper presents a class of novel high-order fully-discrete entropy stable (ES) discontinuous Galerkin (DG) schemes with explicit time discretization. The proposed methodology exploits a critical observation from [4] that the cell…
Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127…
Speech emotion recognition (SER) has been one of the significant tasks in Human-Computer Interaction (HCI) applications. However, it is hard to choose the optimal features and deal with imbalance labeled data. In this article, we…
Algebraic Multigrid (AMG) methods are state-of-the-art algebraic solvers for partial differential equations. Still, their efficiency depends heavily on the choice of suitable parameters and/or ingredients. Paradigmatic examples include the…
In this paper we propose a neural conversation model for conducting dialogues. We demonstrate the use of this model to generate help desk responses, where users are asking questions about PC applications. Our model is distinguished by two…
Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…
Recent large language models (LLMs) exhibit impressive reasoning but often over-think, generating excessively long responses that hinder efficiency. We introduce DIET ( DIfficulty-AwarE Training), a framework that systematically cuts these…
As human-robot collaboration advances, natural and flexible communication methods are essential for effective robot control. Traditional methods relying on a single modality or rigid rules struggle with noisy or misaligned data as well as…
Individuals with Alzheimer's disease (AD) and Alzheimer's disease-related dementia (ADRD) experience memory and thinking changes that impact their ability to use digital daily management tools. For example, adding an event to a digital…
In this paper, we propose a new unified first order hyperbolic model of Newtonian continuum mechanics coupled with electro-dynamics. The model is able to describe the behavior of moving elasto-plastic dielectric solids as well as viscous…
We propose a distributed accelerated primal-dual method with backtracking (D-APDB) for cooperative multi-agent constrained consensus optimization problems over an undirected network of agents, where only those agents connected by an edge…
Recently, end-to-end (E2E) speech recognition has become popular, since it can integrate the acoustic, pronunciation and language models into a single neural network, which outperforms conventional models. Among E2E approaches,…
In this paper, a simple memory limited transmitter for molecular communication is proposed, in which information is encoded in the diffusion rate of the molecules. Taking advantage of memory, the proposed transmitter reduces the ISI problem…
Automatic recognition of dysarthric speech remains a highly challenging task to date. Neuro-motor conditions and co-occurring physical disabilities create difficulty in large-scale data collection for ASR system development. Adapting SSL…