Related papers: Analytical Provisioning for Attention-FFN Disaggre…

Attention mechanisms, primarily designed to capture pairwise correlations between words, have become the backbone of machine learning, expanding beyond natural language processing into other domains. This growth in adaptation comes at the…

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Anatomical brain parcellations dominate rs-fMRI-based Autism Spectrum Disorder (ASD) classification, yet their rigid boundaries may fail to capture the idiosyncratic connectivity patterns that characterise ASD. We present a graph-based deep…

Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…

Federated Learning (FL) revolutionizes collaborative machine learning among Internet of Things (IoT) devices by enabling them to train models collectively while preserving data privacy. FL algorithms fall into two primary categories:…

In large-scale traffic optimization, models based on Macroscopic Fundamental Diagram (MFD) are recognized for their efficiency in broad network analyses. However, they fail to reflect variations in the individual traffic status of each road…

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the…

The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server. FedL ignores two important characteristics of…

Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories by leveraging knowledge from labeled known categories. While existing methods have made notable progress, they often overlook a…

We consider a single large language model (LLM) server that serves a heterogeneous stream of queries belonging to $N$ distinct task types. Queries arrive according to a Poisson process, and each type occurs with a known prior probability.…

Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge…

This paper proposes an anti-interference affine frequency division multiplexing (AFDM) system to ensure reliability and resource efficiency under malicious high-power interference originating from adversarial devices in high-mobility…

With the rapid development of deep learning, recent research on intelligent and interactive mobile applications (e.g., health monitoring, speech recognition) has attracted extensive attention. And these applications necessitate the mobile…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…

Federated learning (FL) allows remote clients to train a global model collaboratively while protecting client privacy. Despite its privacy-preserving benefits, FL has significant drawbacks, including slow convergence, high communication…

Normalizing flows provide an elegant method for obtaining tractable density estimates from distributions by using invertible transformations. The main challenge is to improve the expressivity of the models while keeping the invertibility…

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…

Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this consistency in the generation? We investigate this phenomenon through the lens of probability…

The traditional Kalman filter (KF) is widely applied in control systems, but it relies heavily on the accuracy of the system model and noise parameters, leading to potential performance degradation when facing inaccuracies. To address this…

Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…