Related papers: Tiny but Mighty: A Software-Hardware Co-Design App…

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…

With the emergence of Artificial Intelligence (AI), new attention has been given to implement AI algorithms on resource constrained tiny devices to expand the application domain of IoT. Multimodal Learning has recently become very popular…

Compute-in-memory (CIM) accelerators using non-volatile memory (NVM) devices offer promising solutions for energy-efficient and low-latency Deep Neural Network (DNN) inference execution. However, practical deployment is often hindered by…

Solid-state storage architectures based on NAND or emerging memory devices (SSD), are fundamentally architected and optimized for both reliability and performance. Achieving these simultaneous goals requires co-design of memory components…

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…

Analog in-memory computing (AIMC) is a promising compute paradigm to improve speed and power efficiency of neural network inference beyond the limits of conventional von Neumann-based architectures. However, AIMC introduces fundamental…

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

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…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight…

This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural architecture search (NAS),…

Extreme edge devices or Internet-of-thing nodes require both ultra-low power always-on processing as well as the ability to do on-demand sampling and processing. Moreover, support for IoT applications like voice recognition, machine…

One viable solution for continuous reduction in energy-per-operation is to rethink functionality to cope with uncertainty by adopting computational approaches that are inherently robust to uncertainty. It requires a novel look at data…

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,…

While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary…

This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal…

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant,…

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…

Redundancy of visual tokens in multi-modal large language models (MLLMs) significantly reduces their computational efficiency. Recent approaches, such as resamplers and summarizers, have sought to reduce the number of visual tokens, but at…