Related papers: LoRaFlow: High-Quality Signal Reconstruction using…
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model…
The network flow optimization approach is offered for restoration of grayscale and color images corrupted by noise. The Ising models are used as a statistical background of the proposed method. The new multiresolution network flow minimum…
LoRa has become a cornerstone for city-wide IoT applications due to its long-range, low-power communication. It achieves extended transmission by spreading symbols over multiple samples, with redundancy controlled by the Spreading Factor…
We consider a multipoint-to-point network in which sensors periodically send measurements to a gateway. The system uses Long Range (LoRa) communications in a frequency band with duty-cycle limits. Our aim is to enhance the reliability of…
We present Wi-Lo, which allows to convert an ordinary 802.11 (WiFi) access point into an internet of things (IoT) gateway supporting the low-power wide area network (LPWAN) technology LoRa in the downlink. Our Wi-Lo system only requires a…
Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by…
Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…
LoRa is one of the promising techniques for enabling Low Power Wide Area Networks (LPWANs) for future Internet-of-Things (IoT) devices. Although LoRa allows flexible adaptations of coverage and data rates, it is subject to intrinsic types…
Considering the microphone is easily affected by noise and soundproof materials, the radio frequency (RF) signal is a promising candidate to recover audio as it is immune to noise and can traverse many soundproof objects. In this paper, we…
Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL…
This paper addresses the critical issue of spectrum scarcity and the need to support diverse services, including communication and learning tasks, by presenting a reconfigurable intelligent surface (RIS)-aided wireless network framework…
Recent advancements in video restoration have focused on recovering high-quality video frames from low-quality inputs. Compared with static images, the performance of video restoration significantly depends on efficient exploitation of…
LoRa networks have been deployed all over the world and are a major enabling wireless technology for the Internet of Things (IoT). Massive connectivity applications such as smart metering, agriculture, and supply chain \& logistics are most…
Recent advancements in LLM post-training, particularly through reinforcement learning and preference optimization, are key to boosting their reasoning capabilities. However, these methods often suffer from low sample efficiency and a…
The Internet of Things (IoT) revolution demands scalable, energy-efficient communication protocols supporting widespread device deployments. The LoRa technology, coupled with the LoRaWAN protocol, has emerged as a leading Low Power Wide…
We address the problem of sparse recovery in an online setting, where random linear measurements of a sparse signal are revealed sequentially and the objective is to recover the underlying signal. We propose a reweighted least squares (RLS)…
Low-rank adaptations (LoRA) are widely used to fine-tune large models across various domains for specific downstream tasks. While task-specific LoRAs are often available, concerns about data privacy and intellectual property can restrict…
To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to…
Deep neural networks for event-based video reconstruction often suffer from a lack of interpretability and have high memory demands. A lightweight network called CISTA-LSTC has recently been introduced showing that high-quality…
Most of the existing methods for sparse signal recovery assume a static system: the unknown signal is a finite-length vector for which a fixed set of linear measurements and a sparse representation basis are available and an L1-norm…