Related papers: LoRaFlow: High-Quality Signal Reconstruction using…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a…

The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous…

This paper advocates a fluid antenna system (FAS)-assisted long-range communication (LoRa-FAS) for Internet-of-Things (IoT) applications. \textcolor{blue}{In the proposed system, FAS provides spatial diversity gains for LoRa, eliminating…

Reconstructing high-quality magnetic resonance images (MRI) from undersampled raw data is of great interest from both technical and clinical point of views. To this date, however, it is still a mathematically and computationally challenging…

Reinforcement learning (RL) has become the pivotal post-training technique for large language model (LLM). Effectively scaling reinforcement learning is now the key to unlocking advanced reasoning capabilities and ensuring safe,…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

LoRaWAN is a compelling low-cost solution for large-scale indoor Internet of Things (IoT) data backhaul, owing to its strong penetration capability and low power consumption. However, its default pure ALOHA access mechanism leads to severe…

The problem of reconstructing a sparse signal vector from magnitude-only measurements (a.k.a., compressive phase retrieval), emerges naturally in diverse applications, but it is NP-hard in general. Building on recent advances in nonconvex…

Many new narrowband low-power wide-area networks (LPWANs) (e.g., LoRaWAN, Sigfox) have opted to use pure ALOHA-like access for its reduced control overhead and asynchronous transmissions. Although asynchronous access reduces the energy…

We consider the robust phase retrieval problem of recovering the unknown signal from the magnitude-only measurements, where the measurements can be contaminated by both sparse arbitrary corruption and bounded random noise. We propose a new…

Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem that fundamentally limits denoising performance. Existing simulated-supervised discriminative learning (SimSDL) and…

We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suffer from incomplete scene initialization for dynamic…

Recovering a signal from its Fourier intensity underlies many important applications, including lensless imaging and imaging through scattering media. Conventional algorithms for retrieving the phase suffer when noise is present but display…

Radio frequency fingerprint identification (RFFI) can classify wireless devices by analyzing the signal distortions caused by the intrinsic hardware impairments. State-of-the-art neural networks have been adopted for RFFI. However, many…

Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications. Existing underwater image enhancement methods mainly focus on image quality improvement, ignoring the effect…

Low-Rank Adaptation (LoRA) has become the leading Parameter-Efficient Fine-Tuning (PEFT) method for Large Language Models (LLMs), as it significantly reduces GPU memory usage while maintaining competitive fine-tuned model quality on…

Neural network pruning is essential for reducing model complexity to enable deployment on resource constrained hardware. While performance loss of pruned networks is often attributed to the removal of critical parameters, we identify signal…

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…

Applying speech super-resolution (SR) to recordings with severely low sampling rates is a critical challenge in digital archiving and investigative audio recovery. In these scenarios, the input lacks essential acoustic cues. Consequently,…