Related papers: LoRaFlow: High-Quality Signal Reconstruction using…
Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in…
Efficient fine-tuning of pre-trained convolutional neural network (CNN) models using local data is essential for providing high-quality services to users using ubiquitous and resource-limited Internet of Things (IoT) devices. Low-Rank…
Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…
Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…
Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event…
LoRa is a widely recognized modulation technology in the field of low power wide area networks (LPWANs). However, the data rate of LoRa is too low to satisfy the requirements of Internet of Things applications. To address this issue, we…
Rectified flow is a generative model that learns smooth transport mappings between two distributions through an ordinary differential equation (ODE). Unlike diffusion-based generative models, which require costly numerical integration of a…
Low Power Wide Area Networks (LPWAN) are wireless connectivity solutions for Internet-of-Things (IoT) applications, including industrial automation. Among the several LPWAN technologies, LoRaWAN has been extensively addressed by the…
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both training and…
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging…
Flow matching has recently emerged as a powerful alternative to diffusion models, providing a continuous-time formulation for generative modeling and representation learning. Yet, we show that this framework suffers from a fundamental…
Reinforcement learning (RL) in few-shot scenarios with limited sensor data is challenging due to insufficient training samples, particularly in applications like Dynamic Voltage and Frequency Scaling (DVFS) where sensor readings are…
Low Power Wide Area (LPWA) networks are making spectacular progress from design, standardisation, to commercialisation. At this time of fast-paced adoption, it is of utmost importance to analyse how well these technologies will scale as the…
Accurate and real-time radio map (RM) generation is crucial for next-generation wireless systems, yet diffusion-based approaches often suffer from large model sizes, slow iterative denoising, and high inference latency, which hinder…
Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…
Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend…
Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for…
Enhancing RAW images captured under low light conditions is a challenging task. Recent deep learning based RAW enhancement methods have shifted from using real paired data to relying on synthetic datasets. These synthetic datasets are…
Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned…
This paper studies a specific low-power wireless technology capable of reaching a long range, namely LoRa. Such a technology can be used by different applications in cities involving many transmitting devices while requiring loose…