Related papers: A Deployment-Friendly Foundational Framework for E…

Glomerular pathology is central to the diagnosis and prognosis of renal diseases, yet the heterogeneity of glomerular morphology and fine-grained lesion patterns remain challenging for current AI approaches. We present GloPath, an…

Differentiable simulation of soft bodies is a foundation for system identification, trajectory optimization, and Real2Sim transfer. Yet, existing methods such as the differentiable Projective Dynamics (DiffPD) struggle when faced with…

Progress in a research field can be hard to assess, in particular when many concurrent methods are proposed in a short period of time. This is the case in digital pathology, where many foundation models have been released recently to serve…

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

One major technical challenge for modern analytical database systems is how to leverage GPU to exploit their massive parallelism and high bandwidth. Yet, existing GPU-driven database engines suffer from inefficiencies caused by frequent…

Our goal in this dissertation is to provide tools, programming models, and system support for PIM architectures (with a focus on DRAM-based solutions), to ease the adoption of PIM in current and future systems. To this end, we make at least…

Parameter-efficient fine-tuning (PEFT) methods reduce the computational costs of updating deep learning models by minimizing the number of additional parameters used to adapt a model to a down- stream task. While extensively researched in…

Pathology foundation models (PFMs) have demonstrated strong representational capabilities through self-supervised pre-training on large-scale, unannotated histopathology image datasets. However, their diverse yet opaque pretraining…

This paper introduces an efficient Vision-Language Model (VLM) pipeline specifically optimized for deployment on embedded devices, such as those used in robotics and autonomous driving. The pipeline significantly reduces the computational…

The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, running latency correspondingly increases, presenting a…

Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models…

In digital pathology, whole-slide images routinely exceed gigapixel resolution, making computationally intensive generative super-resolution (SR) impractical for routine deployment. We introduce CAFlow, an adaptive-depth single-step…

Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live, work, and interact with the world. Due to the…

With the advent of large pre-trained transformer models, fine-tuning these models for various downstream tasks is a critical problem. Paucity of training data, the existence of data silos, and stringent privacy constraints exacerbate this…

Machine learning approaches have the potential to approximate Density Functional Theory (DFT) for atomistic simulations in a computationally efficient manner, which could dramatically increase the impact of computational simulations on…

Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly coupled clusters, limiting participation to well-resourced institutions. While Decentralized Diffusion Models (DDM) enable…

Matrix multiplication is a fundamental kernel in large-scale artificial intelligence and scientific computing, but its performance on conventional electronic accelerators is increasingly constrained by memory bandwidth and energy…

Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their use in many applications, especially those that depend on…

Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their…

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer…