Related papers: ML-Based Automata Simplification for Symbolic Acce…

Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training…

In recent years, there has been increasing interest in using formal methods-based techniques to safely achieve temporal tasks, such as timed sequence of goals, or patrolling objectives. Such tasks are often expressed in real-time logics…

Automatic Traffic Sign Recognition is paramount in modern transportation systems, motivating several research endeavors to focus on performance improvement by utilizing large-scale datasets. As the appearance of traffic signs varies across…

For FPGA-based neural network accelerators, digital signal processing (DSP) blocks have traditionally been the cornerstone for handling multiplications. This paper introduces LUTMUL, which harnesses the potential of look-up tables (LUTs)…

Lifelong SLAM considers long-term operation of a robot where already mapped locations are revisited many times in changing environments. As a result, traditional graph-based SLAM approaches eventually become extremely slow due to the…

While there is a large body of research on efficient processing of deep neural networks (DNNs), ultra-low-latency realization of these models for applications with stringent, sub-microsecond latency requirements continues to be an…

Robotic Process Automation (RPA) systems face challenges in handling complex processes and diverse screen layouts that require advanced human-like decision-making capabilities. These systems typically rely on pixel-level encoding through…

Recurrent Neural Networks (RNNs) are vital for sequential data processing. Long Short-Term Memory Autoencoders (LSTM-AEs) are particularly effective for unsupervised anomaly detection in time-series data. However, inherent sequential…

Reliable and accurate localization and mapping are key components of most autonomous systems. Besides geometric information about the mapped environment, the semantics plays an important role to enable intelligent navigation behaviors. In…

Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to…

In this paper, we present an efficient visual SLAM system designed to tackle both short-term and long-term illumination challenges. Our system adopts a hybrid approach that combines deep learning techniques for feature detection and…

Reconstructing visual information from brain activity via computer vision technology provides an intuitive understanding of visual neural mechanisms. Despite progress in decoding fMRI data with generative models, achieving accurate…

Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have…

Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependent sampling mechanism introduces irregular memory access…

Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to preserve accuracy. In contrast, one-shot compression methods…

It is well-established that many iterative sparse reconstruction algorithms can be unrolled to yield a learnable neural network for improved empirical performance. A prime example is learned ISTA (LISTA) where weights, step sizes and…

The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large models and the instability caused by heterogeneous (non-IID) client data. Conventional pruning…

Embedded Field-Programmable Gate Arrays (eFPGAs) allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget compared with traditional FPGA platforms. However, the limited eFPGA logic and…

Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing machine learning architectures often struggle to represent…

The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt…