Related papers: On the Behavior of RObust Header Compression U-mod…

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…

In multiuser multiple-input multiple-output (MU-MIMO) systems, channel correlation is detrimental to system performance. We demonstrate that widely used, yet overly simplified, correlation models that generate identical correlation profiles…

To access an unlicensed channel Wi-Fi follows Listen Before Talk (LBT) mechanism whereas LTE-U adopts ON-OFF duty cycled mechanism to fairly share the channel with Wi-Fi. These contrasting mechanisms result in quite different performance…

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…

We study the effect of stochastic wireless channel models on the connectivity of ad hoc networks. Unlike in the deterministic geometric disk model where nodes connect if they are within a certain distance from each other, stochastic models…

Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and tend to form clusters. While prior work has established clustering behavior for single-head…

We consider the situation in which a transmitter attempts to communicate reliably over a discrete memoryless channel while simultaneously ensuring covertness (low probability of detection) with respect to a warden, who observes the signals…

This paper investigates the formation control problem of heterogeneous, autonomous agents that communicate over a wireless multiple access channel. Instead of avoiding interference through orthogonal node-to-node transmissions, we exploit…

The purpose of this study is to investigate how homophily, memory constraints, and adversarial disruptions collectively shape the resilience and adaptability of complex networks. To achieve this, we develop a new framework that integrates…

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Human brains are commonly modeled as networks of Regions of Interest (ROIs) and their connections for the understanding of brain functions and mental disorders. Recently, Transformer-based models have been studied over different types of…

A single unit (head) is the conventional input feature extractor in deep learning architectures trained on multivariate time series signals. The importance of the fixed-dimensional vector representation generated by the single-head network…

In this paper, we study the problem of dynamic channel allocation for URLLC traffic in a multi-user multi-channel wireless network where urgent packets have to be successfully transmitted in a timely manner. We formulate the problem as a…

Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression. However, these two techniques are traditionally deployed in an isolated manner, leading to significant accuracy drop…

Exploring nonlinear chemical dynamic systems for information processing has emerged as a frontier in chemical and computational research, seeking to replicate the brain's neuromorphic and dynamic functionalities. We have extensively…

Transient gas network simulations can significantly assist in design and operational aspects of gas networks. Models used in these simulations require a detailed framework integrating various models of the network constituents - pipes and…

Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problems. Even though we have a general understanding of the…

With the popularity of the recent Transformer-based models represented by BERT, GPT-3 and ChatGPT, there has been state-of-the-art performance in a range of natural language processing tasks. However, the massive computations, huge memory…

Channel estimation for massive multiple-input multiple-output (MIMO) systems is fundamentally constrained by excessive pilot overhead and high estimation latency. To overcome these obstacles, recent studies have leveraged deep generative…