Related papers: TenonOS: A Self-Generating LibOS-on-LibOS Framewor…
We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text generation works that require re-encoding of the context after…
High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…
Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy…
Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping…
Small devices are frequently used in IoT and smart-city applications to perform periodic dedicated tasks with soft deadlines. This work focuses on developing methods to derive efficient power-management methods for periodic tasks on small…
Edge computing has been emerging as a popular scenario for model inference. However, the inference performance on edge devices (e.g., Multi-Core DSP, FGPA, etc.) suffers from inefficiency due to the lack of highly optimized inference…
Binarized Neural Networks (BNNs) significantly reduce the computation and memory demands with binarized weights and activations compared to full-precision NNs. Executing a layer in a BNN on different devices of a heterogeneous…
Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…
Time-Aware Shaper (TAS) is a time-triggered scheduling mechanism that ensures bounded latency for time-critical Scheduled Traffic (ST) flows. The Linux kernel implementation (a.k.a TAPRIO) has limited capabilities due to varying CPU…
The significant resource demands in LLM serving prompts production clusters to fully utilize heterogeneous hardware by partitioning LLM models across a mix of high-end and low-end GPUs. However, existing parallelization approaches often…
A surge in artificial intelligence and autonomous technologies have increased the demand toward enhanced edge-processing capabilities. Computational complexity and size of state-of-the-art Deep Neural Networks (DNNs) are rising…
Inspired by the pioneering work of Gilles Kahn on concurrent systems, we propose to model timed systems as a network of software components (implemented as real-time processes or tasks), each of which is specified to compute a collection of…
Electronic-photonic computing systems offer immense potential in energy-efficient artificial intelligence (AI) acceleration tasks due to the superior computing speed and efficiency of optics, especially for real-time, low-energy deep neural…
Pushing the frontiers of time-series information processing in the ever-growing domain of edge devices with stringent resources has been impeded by the systems' ability to process information and learn locally on the device. Local…
Symmetric tensor operations arise in a wide variety of computations. However, the benefits of exploiting symmetry in order to reduce storage and computation is in conflict with a desire to simplify memory access patterns. In this paper, we…
Temporal Neural Networks (TNNs) use time as a resource to represent and process information, mimicking the behavior of the mammalian neocortex. This work focuses on implementing TNNs using off-the-shelf digital CMOS technology. A…
Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…
Shifting towards renewable energy sources and reducing carbon emissions necessitate sophisticated energy system planning, optimization, and extension. Energy systems optimization models (ESOMs) often form the basis for political and…
Even well-designed software systems suffer from chronic performance degradation, also named "software aging", due to internal (e.g. software bugs) and external (e.g. resource exhaustion) impairments. These chronic problems often fly under…
We introduce NebulOS, a Big Data platform that allows a cluster of Linux machines to be treated as a single computer. With NebulOS, the process of writing a massively parallel program for a datacenter is no more complicated than writing a…