Related papers: MPM: Mutual Pair Merging for Efficient Vision Tran…

Memristive Processing In-Memory (PIM) is one of the promising techniques for overcoming the Von-Neumann bottleneck. Reduction of data transfer between processor and memory and data processing by memristors in data-intensive applications…

Masked generative models (MGMs) have emerged as a powerful framework for image synthesis, combining parallel decoding with strong bidirectional context modeling. However, generating high-quality samples typically requires many iterative…

Vision Transformers (ViTs) have emerged as powerful backbones in computer vision, outperforming many traditional CNNs. However, their computational overhead, largely attributed to the self-attention mechanism, makes deployment on…

Decoder-only Transformer models such as GPT have demonstrated exceptional performance in text generation, by autoregressively predicting the next token. However, the efficacy of running GPT on current hardware systems is bounded by low…

We present a novel, practical approach to speed up sparse matrix-vector multiplication (SpMVM) on GPUs. The novel key idea is to apply lossless entropy coding to further compress the sparse matrix when stored in one of the commonly…

Recently DRAM-based PIMs (processing-in-memories) with unmodified cell arrays have demonstrated impressive performance for accelerating AI applications. However, due to the very restrictive hardware constraints, PIM remains an accelerator…

Though U-Net has achieved tremendous success in medical image segmentation tasks, it lacks the ability to explicitly model long-range dependencies. Therefore, Vision Transformers have emerged as alternative segmentation structures recently,…

The incorporation of high-performance optoelectronic devices into photonic neuromorphic processors can substantially accelerate computationally intensive operations in machine learning (ML) algorithms. However, the conventional device…

Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for image and video segmentation, such as EoMT and VidEoMT, achieve…

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Magnetic particle imaging (MPI) offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used…

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

We present a novel framework for designing multiplierless kernel machines that can be used on resource-constrained platforms like intelligent edge devices. The framework uses a piecewise linear (PWL) approximation based on a margin…

We propose a novel scheme that allows MIMO system to modulate a set of permutation matrices to send more information bits, extending our initial work on the topic. This system is called Permutation Matrix Modulation (PMM). The basic idea is…

Processing-in-DRAM (DRAM-PIM) has emerged as a promising technology for accelerating memory-intensive operations in modern applications, such as Large Language Models (LLMs). Despite its potential, current software stacks for DRAM-PIM face…

Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively…

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…

For over a decade now we have been witnessing the success of {\em massive parallel computation} (MPC) frameworks, such as MapReduce, Hadoop, Dryad, or Spark. One of the reasons for their success is the fact that these frameworks are able to…