As demand for EVs (Electric Vehicles), WSNs (Wireless Sensor Networks), and IoT (Internet of Things) devices continues to grow, efficient battery health monitoring has emerged as a critical requirement. Conventional BMS (Battery Management System) designs rely on wired, centralized architectures, which are not only costly and less scalable but also highly prone to operational failures. To mitigate these inherent drawbacks, recent studies have shifted toward exploring wireless, low-power, and contactless alternatives. This paper reviews emerging sensing solutions and […]

Ver mais

My research work is mostly in Multilingual NLP, but it’s very tough to find a lot of options to submit my paper. ACL conferences or TACL, CL journals are prestigious and very well known. However, I find it very difficult to find any other good venues focused on this research area. Are there any venues which are not in generic AI but accept NLP-focused work mostly? I don’t mind if they’re journals, however conferences would be good. submitted […]

Ver mais

Driven by the right to be forgotten (RTBF), machine unlearning has become an essential requirement for privacy-preserving machine learning. However, its realization in decentralized federated learning (DFL) remains largely unexplored. In DFL, clients exchange local updates only with neighbors, causing model information to propagate and mix across the network. As a result, when a client requests data deletion, its influence is implicitly embedded throughout the system, making removal difficult without centralized coordination. We propose a novel certified unlearning […]

Ver mais

arXiv:2601.03244v1 Announce Type: new Abstract: Many important problems in science and engineering involve inferring a signal from noisy and/or incomplete observations, where the observation process is known. Historically, this problem has been tackled using hand-crafted regularization (e.g., sparsity, total-variation) to obtain meaningful estimates. Recent data-driven methods often offer better solutions by directly learning a solver from examples of ground-truth signals and associated observations. However, in many real-world applications, obtaining ground-truth references for training is expensive or impossible. Self-supervised […]

Ver mais

Parsing with Haskell (Part 1): Lexing with Alex This is the first of the two parts of our Parsing with Haskell series. Looking for the second part instead? You can find it here. This two-part tutorial will look into two tools often used together by Haskellers to parse programs: Alex and Happy. We’ll use them to parse a small programming language from scratch. Both Alex and Happy are industrial-strength tools powerful enough to parse even Haskell itself. At […]

Ver mais

Instead of catching you off-guard with a jump scare this Halloween season, EFF is here to catch you up on the latest digital rights news with our EFFector newsletter! In this issue, we’re helping you take control of your online privacy with Opt Out October; explaining the UK’s attack on encryption and why it’s bad for all users; and covering shocking new details about an abortion surveillance case in Texas. Prefer to listen in? Check out our audio […]

Ver mais

Everyone loves ChatGPT, right? And hey, shoutout to DeepSeek Hero too. But what about the unsung heroes of the AI world—those open-source large language models (LLMs) quietly powering innovation behind the scenes? While models like Meta’s LLaMA might ring a bell for some, there’s a whole family of open-source LLMs you may not have heard of yet—like Mistral, Gemma, Qwen, and even open versions of DeepSeek. Sure, most non-CS folks won’t download massive multi-gigabyte models just to have […]

Ver mais