Related papers: Locate: Low-Power Viterbi Decoder Exploration usin…

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Visual Place Recognition (VPR) is a critical task for performing global re-localization in visual perception systems. It requires the ability to accurately recognize a previously visited location under variations such as illumination,…

Adapter-based approaches have garnered attention for fine-tuning pre-trained Vision-Language Models (VLMs) on few-shot classification tasks. These methods strive to develop a lightweight module that better aligns visual and (category)…

The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at…

The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization,…

State-of-the-art Automatic Speech Recognition (ASR) systems are known to exhibit disparate performance on varying speech accents. To improve performance on a specific target accent, a commonly adopted solution is to finetune the ASR model…

Low-light video enhancement is highly demanding in maintaining spatiotemporal color consistency. Therefore, improving the accuracy of color mapping and keeping the latency low is challenging. Based on this, we propose incorporating…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

We propose a new descriptor for local atomic environments, to be used in combination with machine learning models for the construction of interatomic potentials. The Local Atomic Tensors Trainable Expansion (LATTE) allows for the efficient…

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…

The problem of optimal power allocation among light emitting diode (LED) transmitters in a visible light positioning (VLP) system is considered for the purpose of improving localization performance of visible light communication (VLC)…

Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-context extension have significantly expanded the context…

Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune a VFM to a mixed-precision quantized supernet. The…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic…

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency…

As deep learning models become increasingly bigger and more complex, it is critical to improve model training and inference efficiency. Though a variety of highly optimized libraries and packages (known as DL kernels) have been developed,…

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…

The use of modern Natural Language Processing (NLP) techniques has shown to be beneficial for software engineering tasks, such as vulnerability detection and type inference. However, training deep NLP models requires significant…