Related papers: SISA: A Scale-In Systolic Array for GEMM Accelerat…

This paper presents an LLM-driven, end-to-end workflow that addresses the lack of automation and intelligence in power system transient stability assessment (TSA). The proposed agentic framework integrates large language models (LLMs) with…

LoRA and its variants have become popular parameter-efficient fine-tuning (PEFT) methods due to their ability to avoid excessive computational costs. However, an accuracy gap often exists between PEFT methods and full fine-tuning (FT), and…

State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured…

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

Spiking Neural Networks (SNNs) have emerged as a biologically inspired alternative to conventional deep networks, offering event-driven and energy-efficient computation. However, their throughput remains constrained by the serial update of…

Modular Arrays (MAs) are a promising architecture to enable multi-user communications in next-generation multiple-input multiple-output (MIMO) systems based on extra-large (XL) or gigantic MIMO (gMIMO) deployments, trading off improved…

Current PEFT methods for LLMs can achieve either high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate sparse fine-tuning and observe a remarkable improvement in…

In contemporary software development, the widespread use of indirect calls to achieve dynamic features poses challenges in constructing precise control flow graphs (CFGs), which further impacts the performance of downstream static analysis…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational…

Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks…

Single-snapshot signal processing in sparse linear arrays has become increasingly vital, particularly in dynamic environments like automotive radar systems, where only limited snapshots are available. These arrays are often utilized either…

Coarse-Grain Reconfigurable Arrays (CGRAs) represent emerging low-power architectures designed to accelerate Compute-Intensive Loops (CILs). The effectiveness of CGRAs in providing acceleration relies on the quality of mapping: how…

SMILES-based molecular generative models have been pivotal in drug design but face challenges in fragment-constrained tasks. To address this, the Sequential Attachment-based Fragment Embedding (SAFE) representation was recently introduced…

Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba, that…

Efficient spectrum management in massive-scale wireless networks is increasingly challenged by explosive action spaces and the computational intractability of traditional optimization. This study proposes a Large-Scale LLM-Driven Spectrum…

Selective state space models (SSMs) have rapidly become a compelling backbone for large language models, especially for long-context workloads. Yet in deployment, their inference performance is often bounded by the memory capacity,…

We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces…

Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of…