Related papers: K-PACT: Kernel Planning for Adaptive Context Switc…

As machine learning gets deployed more and more widely, and model sizes continue to grow, improving computational efficiency during model inference has become a key challenge. In many commonly used model architectures, including…

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…

Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…

Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies,…

Wireless Sensor Networks (WSNs) play a pivotal role in enabling Internet of Things (IoT) devices with sensing and actuation capabilities. Operating in remote and resource-constrained environments, these IoT devices face challenges related…

LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across…

Multi-agent collaborative perception is expected to significantly improve perception performance by overcoming the limitations of single-agent perception through exchanging complementary information. However, training a robust collaborative…

Many applications process a stream of tuples over a window duration, and require the results within a specified deadline after the end of the window. For such scenarios, processing tuples intermittently (in batches) instead of eagerly…

Wireless Sensor Networks (WSNs) are used in many application fields, such as military, healthcare, environment surveillance, etc. The WSN OS based on event-driven model doesn't support real-time and multi-task application types and the OSs…

Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that…

Over-estimation of worst-case execution times (WCETs) of real-time tasks leads to poor resource utilization. In a mixed-criticality system (MCS), the over-provisioning of CPU time to accommodate the WCETs of highly critical tasks may lead…

Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that even well-trained MoE models exhibit significantly imbalanced…

Attention is a fundamental computational kernel that accounts for the majority of the workload in transformer and LLM computing. Optimizing dataflow is crucial for enhancing both performance and energy efficiency in attention computation.…

We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data. Our neural network produces sample embeddings that are motivated by--and are at least as expressive as--spectral clustering. Our…

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention…

Distributed Complex Event Processing has emerged as a well-established paradigm to detect situations of interest from basic sensor streams, building an operator graph between sensors and applications. In order to detect event patterns that…

Nowadays the number of available processing cores within computing nodes which are used in recent clustered environments, are growing up with a rapid rate. Despite this trend, the number of available network interfaces in such computing…

This paper introduces ASCENT (context Aware Spectrum Coexistence Design and Implementation) toolset, an advanced context-aware terrestrial satellite spectrum sharing toolset designed for researchers, policymakers, and regulators. It serves…

Linear classifiers with random convolution kernels are computationally efficient methods that need no design or domain knowledge. Unlike deep neural networks, there is no need to hand-craft a network architecture; the kernels are randomly…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…