Related papers: DONUT-hole: DONUT Sparsification by Harnessing Kno…

Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology facilitating the study of macromolecular structures at near-atomic resolution. Recent volumetric segmentation approaches on cryo-ET images have drawn widespread interest in…

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.…

Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. However, real-world documents often feature complex layouts…

The rise of online learning has led to the development of various knowledge tracing (KT) methods. However, existing methods have overlooked the problem of increasing computational cost when utilizing large graphs and long learning…

The rapid growth of e-commerce has intensified the demand for Virtual Try-On (VTO) technologies, enabling customers to realistically visualize products overlaid on their own images. Despite recent advances, existing VTO models face…

Audio-visual learning seeks to enhance the computer's multi-modal perception leveraging the correlation between the auditory and visual modalities. Despite their many useful downstream tasks, such as video retrieval, AR/VR, and…

Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous methods for model compression have been proposed, most focus…

Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure to ensure retrieval efficacy while maintaining computational efficiency. Existing VDR models struggle to…

In recent years, deep neural networks (DNNs) have gained widespread adoption for continuous mobile object detection (OD) tasks, particularly in autonomous systems. However, a prevalent issue in their deployment is the one-size-fits-all…

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning…

Deep operator networks (DeepONets, DONs) offer a distinct advantage over traditional neural networks in their ability to be trained on multi-resolution data. This property becomes especially relevant in real-world scenarios where…

A visually rich document (VRD) utilizes visual features along with linguistic cues to disseminate information. Training a custom extractor that identifies named entities from a document requires a large number of instances of the target…

Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets. Their main drawback however is that these methods are hardly able to recognize visual…

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for…

The recognition of named entities in visually-rich documents (VrD-NER) plays a critical role in various real-world scenarios and applications. However, the research in VrD-NER faces three major challenges: complex document layouts,…

Model pruning is a widely adopted technique to reduce the computational complexity and memory footprint of Deep Neural Networks (DNNs). However, global unstructured pruning often leads to significant degradation in accuracy, typically…

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency.…

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce…

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely…

In this work, we propose a novel deep online correction (DOC) framework for monocular visual odometry. The whole pipeline has two stages: First, depth maps and initial poses are obtained from convolutional neural networks (CNNs) trained in…