相关论文: ODIN: Overcoming Dynamic Interference in iNference…

Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular,…

Online Learning (OL) is a field of research that is increasingly gaining attention both in academia and industry. One of the main challenges of OL is the inherent presence of concept drifts, which are commonly defined as unforeseeable…

It has become routine in neuroscience studies to measure brain networks for different individuals using neuroimaging. These networks are typically expressed as adjacency matrices, with each cell containing a summary of connectivity between…

In online interval scheduling, the input is an online sequence of intervals, and the goal is to accept a maximum number of non-overlapping intervals. In the more general disjoint path allocation problem, the input is a sequence of requests,…

Cyber-security garnered significant attention due to the increased dependency of individuals and organizations on the Internet and their concern about the security and privacy of their online activities. Several previous machine learning…

Precise interference detection and identification are crucial for enhancing the survivability of communication systems in non-cooperative wireless environments. While deep learning (DL) has advanced this field, existing single-task learning…

Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing…

Energy sampling-based interference detection and identification (IDI) methods collide with the limitations of commercial off-the-shelf (COTS) IoT hardware. Moreover, long sensing times, complexity and inability to track concurrent…

In addition to ever-present thermal noise, communication and sensor systems can contain significant amounts of interference with outlier (e.g. impulsive) characteristics. Such outlier interference (including that caused by nonlinear signal…

Projection-based model reduction enables efficient simulation of complex dynamical systems by constructing low-dimensional surrogate models from high-dimensional data. The Operator Inference (OpInf) approach learns such reduced surrogate…

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain,…

In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline…

This paper studies the integration of machine-learned advice in overlay networks in order to adapt their topology to the incoming demand. Such demand-aware systems have recently received much attention, for example in the context of data…

We propose an online debiased lasso (ODL) method for statistical inference in high-dimensional linear models with streaming data. The proposed ODL consists of an efficient computational algorithm for streaming data and approximately normal…

LLM inference latency critically determines user experience and operational costs, directly impacting throughput under SLO constraints. Even brief latency spikes degrade service quality despite acceptable average performance. However,…

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing but exhibit significant performance gaps among different languages. Most existing approaches to address these disparities rely on pretraining or…

Heterogeneous networks (HetNets) have strong interference due to spectrum reuse. This affects the signal-to-interference ratio (SIR) of each user, and hence is one of the limiting factors of network performance. However, in previous works,…

With the development of large language models (LLMs), it has become increasingly important to optimize hardware usage and improve throughput. In this paper, we study the inference optimization of the serving system that deploys LLMs. To…

The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers from low GPU…

Real-time operating systems employ spatial and temporal isolation to guarantee predictability and schedulability of real-time systems on multi-core processors. Any unbounded and uncontrolled cross-core performance interference poses a…