Related papers: TC-SSA: Token Compression via Semantic Slot Aggreg…

Compressed sensing (CS) exploits the sparsity of a signal in order to integrate acquisition and compression. CS theory enables exact reconstruction of a sparse signal from relatively few linear measurements via a suitable nonlinear…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components. Despite considerable progress, effectively calibrating the bias between semantically…

Deep neural networks (DNNs) are the de facto standard for essential use cases, such as image classification, computer vision, and natural language processing. As DNNs and datasets get larger, they require distributed training on…

In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference stemming from excessive visual tokens in multimoal large…

Digital whole slide images (WSIs) are generally captured at microscopic resolution and encompass extensive spatial data. Directly feeding these images to deep learning models is computationally intractable due to memory constraints, while…

Implementation of digital pathology leads to an increased number of whole slide images (WSIs). The large size of WSIs is challenging. Today, WSIs are compressed with codecs like JPEG resulting in several gigabytes per WSI, and large amounts…

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal…

Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia. To optimize system performance in specific scenarios, the Weighted Finite-State Transducer (WFST) is extensively used to…

Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial…

A major obstacle to building models for effective semantic segmentation, and particularly video semantic segmentation, is a lack of large and well annotated datasets. This bottleneck is particularly prohibitive in highly specialized and…

Deep-learning techniques have been used widely to alleviate the labour-intensive and time-consuming manual annotation required for pixel-level tissue characterization. Our previous study introduced an efficient single dynamic network -…

Network data are commonly collected in a variety of applications, representing either directly measured or statistically inferred connections between features of interest. In an increasing number of domains, these networks are collected…

The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific segmentation tasks remains a computational bottleneck. Existing…

Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistically coherent units are disrupted, causing irreversible…

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…

Histopathological whole slide images (WSIs) classification has become a foundation task in medical microscopic imaging processing. Prevailing approaches involve learning WSIs as instance-bag representations, emphasizing significant…

More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Teacher-student compression (TSC), also known as distillation, alleviates…

This paper presents an autoencoder-based neural network architecture to compress histopathological images while retaining the denser and more meaningful representation of the original images. Current research into improving compression…

Whole Slide Image (WSI) classification is often formulated as a Multiple Instance Learning (MIL) problem. Recently, Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However, existing methods…