相关论文: A Deployment-Friendly Foundational Framework for E…

In this paper, we explore a novel image matting task aimed at achieving efficient inference under various computational cost constraints, specifically FLOP limitations, using a single matting network. Existing matting methods which have not…

Whole slide pathology image classification presents challenges due to gigapixel image sizes and limited annotation labels, hindering model generalization. This paper introduces a prompt learning method to adapt large vision-language models…

Current state-of-the-art segmentation models encode entire images before focusing on specific objects. As a result, they waste computational resources - particularly when small objects are to be segmented in high-resolution scenes. We…

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of…

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Pathology foundation models (PFMs) have recently emerged as powerful pretrained encoders for computational pathology, enabling transfer learning across a wide range of downstream tasks. However, systematic comparisons of these models for…

The deep neural network is a research hotspot for histopathological image analysis, which can improve the efficiency and accuracy of diagnosis for pathologists or be used for disease screening. The whole slide pathological image can reach…

Accurate and timely identification of plant leaf diseases is essential for resilient and sustainable agriculture, yet most deep learning approaches rely on large annotated datasets and computationally intensive models that are unsuitable…

Multiple instance learning (MIL) has enabled substantial progress in computational histopathology, where a large amount of patches from gigapixel whole slide images are aggregated into slide-level predictions. Heatmaps are widely used to…

Checkpointing to preserve training states is crucial during the development of Large Foundation Models (LFMs), for training resumption upon various failures or changes in GPU resources and parallelism configurations. In addition, saved…

We present the Lightweight Parallel Foundations (LPF), an interoperable and model-compliant communication layer adhering to a strict performance model of parallel computations. LPF consists of twelve primitives, each with strict performance…

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in…

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their inference efficiency remains a critical bottleneck due to rapidly growing parameters. Recent advances in dynamic computation…

The escalating adoption of diffusion models for applications such as image generation demands efficient parallel inference techniques to manage their substantial computational cost. However, existing diffusion parallelism inference schemes…

In modern low-power embedded platforms, floating-point (FP) operations emerge as a major contributor to the energy consumption of compute-intensive applications with large dynamic range. Experimental evidence shows that 50% of the energy…

Existing dynamic vulnerability patching techniques are not well-suited for embedded devices, especially mission-critical ones such as medical equipment, as they have limited computational power and memory but uninterrupted service…

We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcriptomics through encoders producing biologically grounded representations on both sides of…

Histological artifacts pose challenges for both pathologists and Computer-Aided Diagnosis (CAD) systems, leading to errors in analysis. Current approaches for histological artifact restoration, based on Generative Adversarial Networks…

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…