Related papers: ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency …

Deep neural networks (DNNs) are a type of artificial intelligence models that are inspired by the structure and function of the human brain, designed to process and learn from large amounts of data, making them particularly well-suited for…

Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action…

On-chip buses are typically designed to meet performance constraints at worst-case conditions, including process corner, temperature, IR-drop, and neighboring net switching pattern. This can result in significant performance slack at more…

When applying Dynamic Power Management (DPM) technique to pervasively deployed embedded systems, the technique needs to be very efficient so that it is feasible to implement the technique on low end processor and tight-budget memory.…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

As opposed to conventional training methods tailored to minimize a given statistical metric or task-agnostic loss (e.g., mean squared error), Decision-Focused Learning (DFL) trains machine learning models for optimal performance in…

Large Language Models (LLMs) can perform zero-shot learning on unseen tasks and few-shot learning on complex reasoning tasks. However, resource-limited mobile edge networks struggle to support long-context LLM serving for LLM agents during…

Neural networks with a latency requirement on the order of microseconds, like the ones used at the CERN Large Hadron Collider, are typically deployed on FPGAs fully unrolled and pipelined. A bottleneck for the deployment of such neural…

In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit…

We present hardware/software techniques to intelligently regulate supply voltage and clock frequency of intermittently-computing devices. These devices rely on ambient energy harvesting to power their operation and small capacitors as…

Embedded systems are becoming more in demand to work in dynamic and uncertain environments, and being confined to the strong requirements of real-time. Conventional static scheduling models usually cannot cope with runtime modification in…

Large Language Models (LLMs) are increasingly being integrated into various applications and services running on billions of mobile devices. However, deploying LLMs on resource-limited mobile devices faces a significant challenge due to…

We present a novel application of the machine learning / artificial intelligence method called boosted decision trees to estimate physical quantities on field programmable gate arrays (FPGA). The software package fwXmachina features a new…

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Transformer-based models are becoming deeper and larger recently. For better scalability, an underlying training solution in industry is to split billions of parameters (tensors) into many tasks and then run them across homogeneous…

We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigates error accumulation in parallel decoding, enabling aggressive decoding parallelism while preserving generation quality. Unlike conventional masked…

The metadata service (MDS) sits on the critical path for distributed file system (DFS) operations, and therefore it is key to the overall performance of a large-scale DFS. Common "serverful" MDS architectures, such as a single server or…

Time-domain nonvolatile in-memory computing (TD-nvIMC) offers a promising pathway to reduce data movement and improve energy efficiency by encoding computation in delay rather than voltage or current. This work presents a fully integrated…

Medical vision-language models (VLMs) offer promise for clinical decision support, yet their reliability under distribution shifts remains a major concern for safe deployment. These models often learn task-agnostic correlations due to…

A fairly reliable trend in deep reinforcement learning is that the performance scales with the number of parameters, provided a complimentary scaling in amount of training data. As the appetite for large models increases, it is imperative…