Next week, five teens from Palestine will head to Panama to compete in one of the world's largest youth robotics competitions. To win--and then teach STEM to their peers displaced by the Israel-Hamas war. For the entirety of the past year, as the teenage roboticists of Team Palestine have been working on their latest project, their homeland has been engulfed in Israel's war with Hamas . Earlier this month, that all changed. With a fragile ceasefire in place, Israeli forces began to pull back from parts of Gaza, and the teens put the final touches on the project they hope will bring them victory: a robot that can maneuver through a series of simulated challenges based on the effects of climate change.

Large Language Models (LLMs) have inherent limitations of faithfulness and factuality, commonly referred to as hallucinations. Several benchmarks have been developed that provide a test bed for factuality evaluation within the context of English-centric datasets, while relying on supplementary informative context like web links or text passages but ignoring the available structured factual resources. To this end, Knowledge Graphs (KGs) have been identified as a useful aid for hallucination mitigation, as they provide a structured way to represent the facts about entities and their relations with minimal linguistic overhead. We bridge the lack of KG paths and multilinguality for factual language modeling within the existing hallucination evaluation benchmarks and propose a KG-based multilingual, multihop benchmark called MultiHal framed for generative text evaluation. As part of our data collection pipeline, we mined 140k KG-paths from open-domain KGs, from which we pruned noisy KG-paths, curating a high-quality subset of 25.9k. Our baseline evaluation shows an absolute scale improvement by approximately 0.12 to 0.36 points for the semantic similarity score, 0.16 to 0.36 for NLI entailment and 0.29 to 0.42 for hallucination detection in KG-RAG over vanilla QA across multiple languages and multiple models, demonstrating the potential of KG integration. We anticipate MultiHal will foster future research towards several graph-based hallucination mitigation and fact-checking tasks.

We provide a rigorous random matrix theory analysis of spiked cross-covariance models where the signals across two high-dimensional data channels are partially aligned. These models are motivated by multi-modal learning and form the standard generative setting underlying Partial Least Squares (PLS), a widely used yet theoretically underdeveloped method. We show that the leading singular values of the sample cross-covariance matrix undergo a Baik-Ben Arous-Peche (BBP)-type phase transition, and we characterize the precise thresholds for the emergence of informative components. Our results yield the first sharp asymptotic description of the signal recovery capabilities of PLS in this setting, revealing a fundamental performance gap between PLS and the Bayes-optimal estimator. In particular, we identify the SNR and correlation regimes where PLS fails to recover any signal, despite detectability being possible in principle. These findings clarify the theoretical limits of PLS and provide guidance for the design of reliable multi-modal inference methods in high dimensions.

Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging due to the co-existence of complex algorithmic components such as decentralized communication and local updates. This paper addresses privacy accounting for two decentralized FL algorithms within the $f$-differential privacy ($f$-DP) framework. We develop two new $f$-DP-based accounting methods tailored to decentralized settings: Pairwise Network $f$-DP (PN-$f$-DP), which quantifies privacy leakage between user pairs under random-walk communication, and Secret-based $f$-Local DP (Sec-$f$-LDP), which supports structured noise injection via shared secrets. By combining tools from $f$-DP theory and Markov chain concentration, our accounting framework captures privacy amplification arising from sparse communication, local iterations, and correlated noise. Experiments on synthetic and real datasets demonstrate that our methods yield consistently tighter $(ε,δ)$ bounds and improved utility compared to Rényi DP-based approaches, illustrating the benefits of $f$-DP in decentralized privacy accounting.

Knowledge graph alignment is the task of matching equivalent entities (that is, instances and classes) and relations across two knowledge graphs. Most existing methods focus on pure entity-level alignment, computing the similarity of entities in some embedding space. They lack interpretable reasoning and need training data to work. In this paper, we propose FLORA, a simple yet effective method that (1) is unsupervised, i.e., does not require training data, (2) provides a holistic alignment for entities and relations iteratively, (3) is based on fuzzy logic and thus delivers interpretable results, (4) provably converges, (5) allows dangling entities, i.e., entities without a counterpart in the other KG, and (6) achieves state-of-the-art results on major benchmarks.

Large Language Model (LLM) conditioning refers to instructing an LLM to generate content in accordance with the norms and values of a specific culture, beliefs of a particular political orientation, or any desired text-specified semantic conditioning. Unfortunately, prompt engineering does not ensure that LLMs behave in accordance with a desired conditioning due to the inductive bias of the pre-training and alignment datasets. Prior works have focused on fine-tuning LLMs by directly conditioning the LoRA weights; however, such methods introduce a large number of parameters. As a remedy, we propose Zhyper, a parameter-efficient factorized hypernetwork framework that generates context-aware LoRA adapters from textual descriptions. Experiments on multiple benchmarks show that Zhyper achieves competitive performance with up to 26x fewer parameters than the state-of-the-art baselines. Furthermore, we extend Zhyper to cultural alignment, demonstrating improved generalization to out-of-domain settings and a better capturing of fine-grained contextual values. Large Language Models (LLMs) have transformed Natural Language Processing (NLP), Computer Vision (CV), and machine learning (ML) more broadly. They achieve state-of-the-art performance in text generation and comprehension across diverse domains, including code synthesis (Rozi ` ere et al., 2023), mathematical reasoning (Ahn et al., 2024), scientific writing (Geng et al., 2025; Eger et al., 2025), multimodal tasks such as text-image understanding and generation (Alayrac et al., 2022), and evaluation of machine translation and related tasks (Gu et al., 2025). This success stems from scaling to millions and billions of parameters. However, this scaling requires large computational resources, motivating the search for parameter-efficient fine-tuning (PEFT) techniques. Recent advances have made it possible to adapt LLMs to task-specific criteria, which is crucial for a broader applicability and acceptance of NLP systems. A recent stream of research leverages PEFT techniques (Ding et al., 2023; Weyssow et al., 2023; Prottasha et al., 2024), e.g., Low-Rank Adaptions (LoRA) (Hu et al., 2021) to adapt for desired task-specific values in an LLM. LoRA achieves this by freezing most of the pre-trained model's parameters and introducing trainable low-rank matrices, yielding weight correction terms. However, stand-alone LoRA approaches are primarily tailored for a single-task adaptation and may lose their effectiveness in a setting where an LLM needs to be adapted to various downstream settings.

How much of Europe's oil still comes from Russia? Russia launched dozens of drones and decoy drones across Ukrainian territory, including one that hit a school building in Kyiv. Marco Rubio says implementing Gaza peace deal is'top priority' for Trump Body of'breadwinner' Thai captive held in Gaza returned home Displaced Palestinians forced to live in Gaza's graveyards

Ukraine's president has urged the European Union to back a plan to release billions of euros in frozen Russian cash to help fund the country's defence. As EU leaders met in Brussels, Volodymyr Zelensky said he hoped they would make a positive decision about using €140bn (£122bn) in Russian assets currently held in a Belgian clearing house. The controversial move would would be on top of sanctions the block has imposed on Russia - the latest on Thursday targeting the Kremlin's oil revenues. They followed US measures against Russia's oil industry earlier - the first time President Donald Trump has sanctioned Moscow as he grows frustrated over President Vladimir Putin's refusal to end the war. On Wednesday evening, the US president confirmed that a planned meeting with Putin in Budapest had been shelved indefinitely.

Understanding how life is adapting to urban environments represents an important challenge in evolutionary biology. In this work, we investigate a widely cited example of urban adaptation, Culex pi...

Found Energy, a startup in Boston, aims to harness the energy in scraps of aluminum metal to power industrial processes without fossil fuels. Since 2022, the company has worked to develop ways to rapidly release energy from aluminum on a small scale. Now it's just switched on a much larger version of its aluminum-powered engine, which it claims is the largest aluminum-water reactor ever built. Early next year, it will be installed to supply heat and hydrogen to a tool manufacturing facility in the southeastern US, using the aluminum waste produced by the plant itself as fuel. If everything works as planned, this technology, which uses a catalyst to unlock the energy stored within aluminum metal, could transform a growing share of aluminum scrap into a zero-carbon fuel. Rondo Energy just turned on what it says is the world's largest thermal battery, an energy storage system that can take in electricity and provide a consistent source of heat.