Related papers: Managing Communication Latency-Hiding at Runtime f…

We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept…

Low-latency communication is one of the most important application scenarios in next-generation wireless networks. Often in communication-theoretic studies latency is defined as the time required for the transmission of a packet over a…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Time series modeling, a crucial area in science, often encounters challenges when training Machine Learning (ML) models like Recurrent Neural Networks (RNNs) using the conventional mini-batch training strategy that assumes independent and…

We use random linear network coding (RLNC) based scheme for multipath communication in the presence of lossy links with different delay characteristics to obtain ultra-reliability and low latency. A sliding window version of RLNC is…

Delay-Tolerant Networks (DTNs) have emerged as an exciting research area with a number of useful applications. Most of these applications would benefit greatly by a reduction in the message delivery delay experienced in the network. The…

Despite broad interest in modeling spoken dialogue agents, most approaches are inherently "half-duplex" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or…

The growing integration of AI tools in software development, particularly Large Language Models (LLMs) such as ChatGPT, has revolutionized how developers approach coding tasks. However, achieving high-quality code often requires iterative…

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Scientists have built a variety of covert channels for secretive information transmission with CPU cache and main memory. In this paper, we turn to a lower level in the memory hierarchy, i.e., persistent storage. Most programs store…

Distributed computing frameworks such as MapReduce and Spark are often used to process large-scale data computing jobs. In wireless scenarios, exchanging data among distributed nodes would seriously suffer from the communication bottleneck…

In this paper we demonstrate an approach to model structure and behavior of distributed systems, to map those models to a lightweight execution engine by using a functional programming language and to systematically define and execute tests…

Bootstrapping is a powerful statistical resampling technique for estimating the sampling distribution of an estimator. However, its computational cost becomes prohibitive for large datasets or a high number of resamples. This paper presents…

We present a closed-form expression for the minimal delay that is achievable in a setting that combines a buffer and an erasure code, used to mitigate the packet delay variance. The erasure code is modeled according to the recent…

Linear sequence modeling approaches, such as linear attention, provide advantages like linear-time training and constant-memory inference over sequence lengths. However, existing sequence parallelism (SP) methods are either not optimized…

Python has become a dominant programming language for emerging areas like Machine Learning (ML), Deep Learning (DL), and Data Science (DS). An attractive feature of Python is that it provides easy-to-use programming interface while allowing…

In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in…

Multi-agent systems using large language models (LLMs) have demonstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational…

In this paper, we examine the influence of communication latency on performance of networked control systems. Even though distributed control architectures offer advantages in terms of communication, maintenance costs, and scalability, it…