Related papers: Stop talking to me -- a communication-avoiding ADE…
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…
The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…
Session-based recommendation has received growing attention recently due to the increasing privacy concern. Despite the recent success of neural session-based recommenders, they are typically developed in an offline manner using a static…
The nonequilibrium Green's function (NEGF) formalism is a powerful tool to study the nonequilibrium dynamics of correlated lattice systems, but its applicability to realistic system sizes and long timescales is limited by unfavorable memory…
Affective computing is very important in the relationship between man and machine. In this paper, a system for speech emotion recognition (SER) based on speech signal is proposed, which uses new techniques in different stages of processing.…
Multimodal dialogue emotion recognition captures emotional cues by fusing text, visual, and audio modalities. However, existing approaches still suffer from notable limitations in modeling emotional dependencies and learning multimodal…
We propose Adaptive Compressed Gradient Descent (AdaCGD) - a novel optimization algorithm for communication-efficient training of supervised machine learning models with adaptive compression level. Our approach is inspired by the recently…
Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…
Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by…
Although transformer-based methods have achieved great success in multi-scale temporal pattern interaction modeling, two key challenges limit their further development: (1) Individual time points contain less semantic information, and…
Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience,…
Methods for distributed optimization have received significant attention in recent years owing to their wide applicability in various domains. A distributed optimization method typically consists of two key components: communication and…
In [1] is proposed a simplified DeC method, that, when combined with the residual distribution (RD) framework, allows to construct a high order, explicit FE scheme with continuous approximation avoiding the inversion of the mass matrix for…
Deep learning (DL)-based autoencoder is a potential architecture to implement end-to-end communication systems. In this letter, we first give a brief introduction to the autoencoder-represented communication system. Then, we propose a novel…
An adaptation of the arbitrary high order ADER-DG numerical method with local DG predictor for solving the IVP for a first-order non-linear ODE system is proposed. The proposed numerical method is a completely one-step ODE solver with…
We propose a time-adaptive predictor/multi-corrector method to solve hyperbolic partial differential equations, based on the generalized-$\alpha$ scheme that provides user-control on the numerical dissipation and second-order accuracy in…
Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from…
In this paper, we develop a fully discrete entropy preserving ADER-Discontinuous Galerkin (ADER-DG) method. To obtain this desired result, we equip the space part of the method with entropy correction terms that balance the entropy…
Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…
We present an efficient, accurate, and robust method for simulation of dense suspensions of deformable and rigid particles immersed in Stokesian fluid in two dimensions. We use a well-established boundary integral formulation for the…