Related papers: Morph: ChirpTransformer-based Encoder-decoder Co-d…
Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning…
Secure multi-party computation enables multiple mutually distrusting parties to perform computations on data without revealing the data itself, and has become one of the core technologies behind privacy-preserving machine learning. In this…
With the breakthrough of Transformer-based pre-trained models, the demand for fine-tuning (FT) to adapt the base pre-trained models to downstream applications continues to grow, so it is essential for service providers to reduce the cost of…
Parallel imaging is ubiquitous in MRI, enabling diverse applications such as ultra-high-resolution functional and quantitative imaging with greater temporal resolution or reduced scan times respectively. Successful unfolding is contingent…
Nowadays most research in visual recognition using Convolutional Neural Networks (CNNs) follows the "deeper model with deeper confidence" belief to gain a higher recognition accuracy. At the same time, deeper model brings heavier…
Long Reed-Solomon (RS) codes are desirable for digital communication and storage systems due to their improved error performance, but the high computational complexity of their decoders is a key obstacle to their adoption in practice. As…
This paper investigates a joint beamforming design in a multiuser multiple-input single-output (MISO) communication network aided with an intelligent reflecting surface (IRS) panel. The symbol-level precoding (SLP) is adopted to enhance the…
Fair-density parity-check (FDPC) codes have been recently introduced demonstrating improved performance compared to low-density parity-check (LDPC) codes standardized in 5G systems particularly in high-rate regimes. In this paper, we…
Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and…
LoRa is a popular low-power wide-area network (LPWAN) technology that uses spread-spectrum to achieve long-range connectivity and resilience to noise and interference. For energy efficiency reasons, LoRa adopts a pure ALOHA access scheme,…
Purpose: To develop a method for optimizing pulsed saturation transfer MR fingerprinting (ST MRF) acquisition. Methods: The Cram\'er-Rao bound (CRB) for variance assessment was employed on Bloch-McConnell-based simulated signals, followed…
Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resource constraints and…
Ultra-low-field (ULF, <0.1 T) magnetic resonance imaging (MRI) systems offer advantages in cost, portability, and accessibility, but their current utility is still limited by low signal-to-noise ratio (SNR). Deep learning (DL)-based…
Mixed-signal machine-learning classification has recently been demonstrated as an efficient alternative for classification with power expensive digital circuits. In this paper, a high-COnfidence high-REsolution (CORE) mixed-signal…
In this work, we develop a new iterative turbo receiver for LDPC-coded multi-antenna systems based on semidefinite relaxation (SDR). For a classical turbo receiver, forward error correction (FEC) code is only used at decoder. Nonetheless,…
Chart-to-code generation is a critical task in automated data visualization, translating complex chart structures into executable programs. While recent Multi-modal Large Language Models (MLLMs) improve chart representation, existing…
Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models for its good performance and computational efficiency. LoRA injects a product of two trainable…
Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are limited due to the inefficiency in Softmax and Layer…
Regenerating codes provide an efficient way to recover data at failed nodes in distributed storage systems. It has been shown that regenerating codes can be designed to minimize the per-node storage (called MSR) or minimize the…
We present a transformer-based speech-declipping model that effectively recovers clipped signals across a wide range of input signal-to-distortion ratios (SDRs). While recent time-domain deep neural network (DNN)-based declippers have…