An important use case of next-generation wireless systems is device-edge co-inference, where a semantic task is partitioned between a device and an edge server. The device carries out data collection and partial processing of the data, while the remote server completes the given task based on information received from the device. It is often required that processing and communication be run as efficiently as possible at the device, while more computing resources are available at the edge. To address such scenarios, we introduce a new system solution, termed neuromorphic wireless device-edge co-inference. According to it, the device runs sensing, processing, and communication units using neuromorphic hardware, while the server employs conventional radio and computing technologies. The proposed system is designed using a transmitter-centric information-theoretic criterion that targets a reduction of the communication overhead, while retaining the most relevant information for the end-to-end semantic task of interest. Numerical results on standard data sets validate the proposed architecture, and a preliminary testbed realization is reported.

The effectiveness of Voting Advice Applications (VAA) is often compromised by the length of their questionnaires. To address user fatigue and incomplete responses, some applications (such as the Swiss Smartvote) offer a condensed version of their questionnaire. However, these condensed versions can not ensure the accuracy of recommended parties or candidates, which we show to remain below 40%. To tackle these limitations, this work introduces an adaptive questionnaire approach that selects subsequent questions based on users' previous answers, aiming to enhance recommendation accuracy while reducing the number of questions posed to the voters. Our method uses an encoder and decoder module to predict missing values at any completion stage, leveraging a two-dimensional latent space reflective of political science's traditional methods for visualizing political orientations. Additionally, a selector module is proposed to determine the most informative subsequent question based on the voter's current position in the latent space and the remaining unanswered questions. We validated our approach using the Smartvote dataset from the Swiss Federal elections in 2019, testing various spatial models and selection methods to optimize the system's predictive accuracy. Our findings indicate that employing the IDEAL model both as encoder and decoder, combined with a PosteriorRMSE method for question selection, significantly improves the accuracy of recommendations, achieving 74% accuracy after asking the same number of questions as in the condensed version.

The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations for forgetting include privacy protection, copyright protection, elimination of biases and discrimination, and prevention of harmful content generation. Effective digital forgetting has to be effective (meaning how well the new model has forgotten the undesired knowledge/behavior), retain the performance of the original model on the desirable tasks, and be scalable (in particular forgetting has to be more efficient than retraining from scratch on just the tasks/data to be retained). This survey focuses on forgetting in large language models (LLMs). We first provide background on LLMs, including their components, the types of LLMs, and their usual training pipeline. Second, we describe the motivations, types, and desired properties of digital forgetting. Third, we introduce the approaches to digital forgetting in LLMs, among which unlearning methodologies stand out as the state of the art. Fourth, we provide a detailed taxonomy of machine unlearning methods for LLMs, and we survey and compare current approaches. Fifth, we detail datasets, models and metrics used for the evaluation of forgetting, retaining and runtime. Sixth, we discuss challenges in the area. Finally, we provide some concluding remarks.

Media outlets are becoming more partisan and polarized nowadays. In this paper, we identify media bias at the sentence level, and pinpoint bias sentences that intend to sway readers' opinions. As bias sentences are often expressed in a neutral and factual way, considering broader context outside a sentence can help reveal the bias. In particular, we observe that events in a bias sentence need to be understood in associations with other events in the document. Therefore, we propose to construct an event relation graph to explicitly reason about event-event relations for sentence-level bias identification. The designed event relation graph consists of events as nodes and four common types of event relations: coreference, temporal, causal, and subevent relations. Then, we incorporate event relation graph for bias sentences identification in two steps: an event-aware language model is built to inject the events and event relations knowledge into the basic language model via soft labels; further, a relation-aware graph attention network is designed to update sentence embedding with events and event relations information based on hard labels. Experiments on two benchmark datasets demonstrate that our approach with the aid of event relation graph improves both precision and recall of bias sentence identification.

Many statistical analyses, in both observational data and randomized control trials, ask: how does the outcome of interest vary with combinations of observable covariates? How do various drug combinations affect health outcomes, or how does technology adoption depend on incentives and demographics? Our goal is to partition this factorial space into ``pools'' of covariate combinations where the outcome differs across the pools (but not within a pool). Existing approaches (i) search for a single ``optimal'' partition under assumptions about the association between covariates or (ii) sample from the entire set of possible partitions. Both these approaches ignore the reality that, especially with correlation structure in covariates, many ways to partition the covariate space may be statistically indistinguishable, despite very different implications for policy or science. We develop an alternative perspective, called Rashomon Partition Sets (RPSs). Each item in the RPS partitions the space of covariates using a tree-like geometry. RPSs incorporate all partitions that have posterior values near the maximum a posteriori partition, even if they offer substantively different explanations, and do so using a prior that makes no assumptions about associations between covariates. This prior is the $\ell_0$ prior, which we show is minimax optimal. Given the RPS we calculate the posterior of any measurable function of the feature effects vector on outcomes, conditional on being in the RPS. We also characterize approximation error relative to the entire posterior and provide bounds on the size of the RPS. Simulations demonstrate this framework allows for robust conclusions relative to conventional regularization techniques. We apply our method to three empirical settings: price effects on charitable giving, chromosomal structure (telomere length), and the introduction of microfinance.

Bangkok, Thailand – Sheltering from the sun on a street corner, Kridsada Ahjed rues the day he got involved with the loan sharks who now gobble up most of his daily earnings. "I went to the loan sharks because people like me – with no assets or savings – cannot qualify to get help from legitimate banks," Ahjed, a 40-year-old motorcycle taxi driver, told Al Jazeera. "Now almost everything I make in a day goes towards paying the interest on my debt." Kridsada is far from alone. Thailand's household debt reached nearly 87 percent of gross domestic product last year, according to the Bank of Thailand, among the highest on earth.

The U.K. and U.S. governments announced Monday they will work together in safety testing the most powerful artificial intelligence models. An agreement, signed by Michelle Donelan, the U.K. Secretary of State for Science, Innovation and Technology, and U.S. Secretary of Commerce Gina Raimondo, sets out a plan for collaboration between the two governments. "I think of [the agreement] as marking the next chapter in our journey on AI safety, working hand in glove with the United States government," Donelan told TIME in an interview at the British Embassy in Washington, D.C. on Monday. "I see the role of the United States and the U.K. as being the real driving force in what will become a network of institutes eventually." The U.K. and U.S. AI Safety Institutes were established just one day apart, around the inaugural AI Safety Summit hosted by the U.K. government at Bletchley Park in November 2023.

There was the deepfake audio robocall of President Biden telling you to hold your vote. And just last week, a phony video of Donald Trump with Black voters made the rounds. AI deepfakes are a massive problem this election season, and it's easy to get taken -- especially when your news and social feeds are full of this junk. By the way, you're not alone if you have been fooled. Nearly two-thirds of people can't tell the difference between AI-generated images and voices and the real thing.

Retired Navy Adm. William McRaven's nearly 40-year career in the U.S. military has spanned everything from deployments as a Navy SEAL, hunting down high-value targets overseas, commanding U.S Special Operations forces in Iraq and Afghanistan, and advising Presidents George W. Bush and Barack Obama. But McRaven is best known for planning and overseeing the 2011 raid that ended with the death of Osama bin Laden. In December that year, McRaven was named as a runner-up for TIME's Person of the Year for his role in the operation. "There is nobody in the U.S. government that thinks we can kill our way to victory, certainly not the special-operations guys," he told TIME in 2011, "but what happens is, by capturing and killing some of these high-value targets, we buy space and time for the rest of the government to work." After retiring from the U.S. military in 2014, McRaven served as the chancellor of the University of Texas System and has written several books on leadership.

OpenAI has unveiled a tool for cloning people's voices but is holding back on its public release due to concerns about possible misuse in a key election year. Voice Engine can replicate a person's voice based on a 15-second audio sample, according to an OpenAI blog post demonstrating the tool. But the ChatGPT creator is "taking a cautious and informed approach" to the technology and hopes to start a dialogue on "the responsible deployment of synthetic voices", the company said in the blog post published on Friday. "We recognize that generating speech that resembles people's voices has serious risks, which are especially top of mind in an election year," the San Francisco-based start-up said. "We are engaging with U.S. and international partners from across government, media, entertainment, education, civil society and beyond to ensure we are incorporating their feedback as we build."