A small town in the Netherlands hosts the only factory that produces the only chip-making machines that generate a type of light found nowhere naturally on Earth: extreme ultraviolet, a light emitted by young stars in outer space. This light, known as EUV, is the only way to make one of the world's most valuable and important technologies at scale: cutting-edge semiconductor chips. The factory is forbidden from selling its EUV machines to China. Below we explain how the chips are made, why they have become the focus of the US-China trade wars, how Taiwan was drawn into the maelstrom, and what could come next. The answers take us from deep underground to outer space, from the dirtiest places in the world to the cleanest, from the hottest temperatures to the coldest, from man-made structures smaller than a virus to equipment so large it takes three planes to move, and finally, to a state in physics that is two opposites at the same time.

ABSTRACT Natural gas (NG) is relatively a clean source of energy, particularly compared to fossil fuels, and worldwide consumption of NG has been increasing almost linearly in the last two decades. A similar trend can also be seen in Turkey, while another similarity is the high dependence on impor ts for the continuous NG supply. It is crucial to accurately forecast future NG demand (NGD) in Turkey, especially, for import contracts; in this respect, forecasts of monthly NGD for the following year are of utmost importance. In the current study, the h istorical monthly NG consumption data between 2014 and 2024 provided by SOCAR, the local residential NG distribution company for two cities in Turkey, Bursa and Kayseri, was used to determine out - of - sample monthly NGD forecasts for a period of one year and nine months using various time series models, including SARIMA and ETS models, and a novel proposed machine learning method. The proposed method, named Just - in - Time - Learning - Gaussia n Process Regression (JITL - GPR), uses a novel feature representation for t he past NG demand values; instead of using past demand values as column - wise separate features, they are placed on a two - dimensional (2 - D) grid of year - month values. For each test point, a kernel function, tailored for the NGD predictions, is used in GPR t o predict the query point. Since a model is constructed separately for each test point, the proposed method is, indeed, an example of JITL. The JITL - GPR method is easy to use and optimize, and offers a reduction in forecast errors compared to traditional t ime series methods and a state - of - the - art combinat ion model; therefore, it is a promising tool for NGD forecasting in similar settings. INTRODUCTION In the last few decades, there has been a shift in energy sources from fossil fuels to cleaner energy sources, such as wind and solar energy, mainly due to environmental concerns and related government regulations . However, these latter sources are depend ent on w eather conditions and require integration with grid technologies for continuous power generation. Natural gas (NG), typically, consists of (up to) ~95% of methane and 2 - 2.5% ethane - hexane+, with the remain der consist ing of nitrogen, CO NG p ower plants are easy to build and highly reliable, mak ing them invaluable for "clean" energy production. On the other hand, m ost countries depend on imports to maintain t heir NG supplies, and there is a delicate balance between import s and domestic demand . S toring excess import ed gas above actual demand is difficult and would result in economic losses, while import ing less than actual demand could result in a nationwide sh ortage.

Traditional autonomous driving systems often struggle to integrate high-level reasoning with low-level control, resulting in suboptimal and sometimes unsafe driving behaviors. The emergence of Multimodal Large Language Models (MLLMs), which can process both visual and textual data, presents an opportunity to unify perception and reasoning tasks within a single framework. However, effectively embedding precise safety knowledge into MLLMs for autonomous driving remains a significant challenge. To address this, we propose SafeAuto, a novel framework that enhances MLLM-based autonomous driving systems by incorporating both unstructured and structured knowledge. Specifically, we first introduce the Position-Dependent Cross-Entropy (PDCE) loss function, designed to improve the accuracy of low-level control signal predictions when numerical values are represented as text. Second, to ensure safe autonomous driving by explicitly integrating precise safety knowledge into the MLLM, we develop a reasoning component for SafeAuto. This component translates driving safety regulations into first-order logic rules (e.g., "red light => stop") and incorporates these rules into a probabilistic graphical model, such as a Markov Logic Network (MLN). The MLN is trained to verify the predicted next actions using environmental attributes identified by attribute recognition models (e.g., detecting a red light) to form the predicates. Additionally, we construct a Multimodal RAG model that leverages video data, control signals, and environmental attributes to learn more effectively from past similar driving experiences. By integrating PDCE, MLN, and Multimodal RAG, SafeAuto significantly outperforms existing baselines across multiple datasets. This advancement enables more accurate, reliable, and safer autonomous driving systems that learn from experience, obey traffic laws, and perform precise control actions.

Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adversarial attacks remains poorly understood. This work pioneers the integration of adversarial training into QFL, proposing a robust framework, quantum federated adversarial learning (QFAL), where clients collaboratively defend against perturbations by combining local adversarial example generation with federated averaging (FedAvg). We systematically evaluate the interplay between three critical factors: client count (5, 10, 15), adversarial training coverage (0-100%), and adversarial attack perturbation strength (epsilon = 0.01-0.5), using the MNIST dataset. Our experimental results show that while fewer clients often yield higher clean-data accuracy, larger federations can more effectively balance accuracy and robustness when partially adversarially trained. Notably, even limited adversarial coverage (e.g., 20%-50%) can significantly improve resilience to moderate perturbations, though at the cost of reduced baseline performance. Conversely, full adversarial training (100%) may regain high clean accuracy but is vulnerable under stronger attacks. These findings underscore an inherent trade-off between robust and standard objectives, which is further complicated by quantum-specific factors. We conclude that a carefully chosen combination of client count and adversarial coverage is critical for mitigating adversarial vulnerabilities in QFL. Moreover, we highlight opportunities for future research, including adaptive adversarial training schedules, more diverse quantum encoding schemes, and personalized defense strategies to further enhance the robustness-accuracy trade-off in real-world quantum federated environments.

We present WinoMTDE, a new gender bias evaluation test set designed to assess occupational stereotyping and underrepresentation in German machine translation (MT) systems. Building on the automatic evaluation method introduced by arXiv:1906.00591v1, we extend the approach to German, a language with grammatical gender. The WinoMTDE dataset comprises 288 German sentences that are balanced in regard to gender, as well as stereotype, which was annotated using German labor statistics. We conduct a large-scale evaluation of five widely used MT systems and a large language model. Our results reveal persistent bias in most models, with the LLM outperforming traditional systems. The dataset and evaluation code are publicly available under https://github.com/michellekappl/mt_gender_german.

To recognize and mitigate the harms of generative AI systems, it is crucial to consider who is represented in the outputs of generative AI systems and how people are represented. A critical gap emerges when naively improving who is represented, as this does not imply bias mitigation efforts have been applied to address how people are represented. We critically examined this by investigating gender representation in occupation across state-of-the-art large language models. We first show evidence suggesting that over time there have been interventions to models altering the resulting gender distribution, and we find that women are more represented than men when models are prompted to generate biographies or personas. We then demonstrate that representational biases persist in how different genders are represented by examining statistically significant word differences across genders. This results in a proliferation of representational harms, stereotypes, and neoliberalism ideals that, despite existing interventions to increase female representation, reinforce existing systems of oppression.

Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for handling complex tasks such as web shopping, automated email replies, and financial trading. However, these advancements also amplify the risks of adversarial attacks, particularly when LLM agents can access sensitive external functionalities. Moreover, because LLM agents engage in extensive reasoning or planning before executing final actions, manipulating them into performing targeted malicious actions or invoking specific tools remains a significant challenge. Consequently, directly embedding adversarial strings in malicious instructions or injecting malicious prompts into tool interactions has become less effective against modern LLM agents. In this work, we present UDora, a unified red teaming framework designed for LLM Agents that dynamically leverages the agent's own reasoning processes to compel it toward malicious behavior. Specifically, UDora first samples the model's reasoning for the given task, then automatically identifies multiple optimal positions within these reasoning traces to insert targeted perturbations. Subsequently, it uses the modified reasoning as the objective to optimize the adversarial strings. By iteratively applying this process, the LLM agent will then be induced to undertake designated malicious actions or to invoke specific malicious tools. Our approach demonstrates superior effectiveness compared to existing methods across three LLM agent datasets.

While Large Language Models (LLMs) can amplify online misinformation, they also show promise in tackling misinformation. In this paper, we empirically study the capabilities of three LLMs -- ChatGPT, Gemini, and Claude -- in countering political misinformation. We implement a two-step, chain-of-thought prompting approach, where models first identify credible sources for a given claim and then generate persuasive responses. Our findings suggest that models struggle to ground their responses in real news sources, and tend to prefer citing left-leaning sources. We also observe varying degrees of response diversity among models. Our findings highlight concerns about using LLMs for fact-checking through only prompt-engineering, emphasizing the need for more robust guardrails. Our results have implications for both researchers and non-technical users.

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing methods designed to update certain knowledge in LLMs without changing unrelated others. To make selective edits, previous efforts often sought to update a small amount of parameters in some specific layer(s) of a LLM. Nonetheless, in challenging scenarios, they still fall short in making successful edits while preserving knowledge irrelevant to the updates simultaneously, resulting in a notable editing-locality trade-off. In this work, we question if the trade-offs are caused by the fact that parameter-based updates have a global effect, i.e., edited parameters affect all inputs indiscriminately. In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge editing. While being effective to enhance an LLM's general ability as demonstrated in the previous work, we theoretically show that this linear update imposes a tension in editing-locality trade-off. Subsequently, BaFT is proposed to break the linearity. BaFT computes a weight for each basis that spans a dimension of the subspace based on the input representation. This input-dependent weighting mechanism allows BaFT to manage different types of knowledge in an adaptive way, thereby achieving a better editing-locality trade-off. Experiments on three LLMs with five editing benchmarks in diverse scenarios show the superiority of our method.

I NPUT S PECIFIC N EURAL N ETWORKS A P REPRINT Asghar Jadoon The University of Texas at Austin Austin TX, USA D. Thomas Seidl Sandia National Laboratories Albuquerque NM, USA Reese E. Jones Sandia National Laboratories Livermore CA, USA Jan Fuhg The University of Texas at Austin Austin TX, USA February 2025 Abstract Neural networks have emerged as powerful tools for mapping between inputs and outputs. However, their black-box nature limits the ability to encode or impose specific structural relationships between inputs and outputs. While various studies have introduced architectures that ensure the network's output adheres to a particular form in relation to certain inputs, the majority of these approaches impose constraints on only a single set of inputs, leaving others unconstrained. This paper introduces a novel neural network architecture, termed the Input Specific Neural Network (ISNN), which extends this concept by allowing scalar-valued outputs to be subject to multiple constraints. Specifically, the ISNN can enforce convexity in some inputs, non-decreasing monotonicity combined with convexity with respect to others, and simple non-decreasing monotonicity or arbitrary relationships with additional inputs. To the best of our knowledge, this is the first work that proposes a framework that simultaneously comprehensively imposes all these constraints. The paper presents two distinct ISNN architectures, along with equations for the first and second derivatives of the output with respect to the inputs. These networks are broadly applicable. In this work, we restrict their usage to solving problems in computational mechanics. In particular, we show how they can be effectively applied to fitting data-driven constitutive models. We remark, that due to their increased ability to implicitly model constraints, we can show that ISNNs require fewer inputs than existing input convex neural networks when modeling polyconvex hyperelastic functions. We then embed our trained data-driven constitutive laws into a finite element solver where significant time savings can be achieved by using explicit manual differentiation using the derived equations as opposed to automatic differentiation. Manual differentiation also enables seamless employment of trained ISNNs in commercial solvers where automatic differentiation may not be possible. We also show how ISNNs can be used to learn structural relationships between inputs and outputs via a binary gating mechanism.