Five former US officials, including a former top military lawyer, have criticised the Pentagon for not acknowledging potential American involvement in a deadly strike on an Iranian school earlier this year. Some of those officials said it was highly unusual not to release even basic details of the strike after such a length of time. A missile hit a primary school in Minab during the opening salvos of the US-Israeli war on February 28, killing 168 people including around 110 children according to Iranian officials. In the two months since then the Pentagon has said only that the incident is under investigation. US media reported in early March that US military investigators believed American forces were likely responsible for hitting the school unintentionally but had not reached a final conclusion.

China races to build record biobank to rival U.S. drugs research Biobanks store masses of biomedical data such as clinical records, genome sequences and other long-term health metrics that research and drug development depend on. As a fledgling researcher in U.S., Zhang Li was struck by the efficiency of extracting human tissue in the morning and mining it for data the same afternoon. Such a streamlined process had been missing from his years of training as a bio data scientist in China. Inspired, he returned home to Beijing to join the Chinese Institute for Brain Research and launch a national database that will collect blood and DNA samples from 33,000 children to help identify patterns of brain disease and their risk factors. "Biomedical data is extremely valuable and is fundamental for us to find solutions to diseases and to delay aging," said Zhang, surrounded by robotic arms carefully organizing blood samples.

Kim Jong Un praises troops who'self-blasted' to avoid capture by Ukraine Kim Jong Un has praised North Korean soldiers who killed themselves by detonating their grenades while fighting for Russia against Ukraine, confirming a long-suspected battlefield policy. In a speech this week, the North Korean leader said those who unhesitatingly opted for self-blasting, suicide attack, in order to defend the great honour were heroes. South Korea estimates at least 15,000 North Koreans have been sent to help Russia recapture parts of western Kursk, and more than 6,000 have been killed so far. Neither Pyongyang nor Moscow have confirmed the numbers. Intelligence agencies and defectors have said the soldiers were under Pyongyang's orders to kill themselves rather than be taken prisoner by Ukraine.

The relationship between perception and inference, as postulated by Helmholtz in the 19th century, is paralleled in modern machine learning by generative models like Variational Autoencoders (VAEs) and their hierarchical variants. Here, we evaluate the role of hierarchical inference and its alignment with brain function in the domain of motion perception. We first introduce a novel synthetic data framework, Retinal Optic Flow Learning (ROFL), which enables control over motion statistics and their causes. We then present a new hierarchical VAE and test it against alternative models on two downstream tasks: (i) predicting ground truth causes of retinal optic flow (e.g., self-motion); and (ii) predicting the responses of neurons in the motion processing pathway of primates. We manipulate the model architectures (hierarchical versus non-hierarchical), loss functions, and the causal structure of the motion stimuli.

We propose a novel framework for analyzing the dynamics of distribution shift in real-world systems that captures the feedback loop between learning algorithms and the distributions on which they are deployed.

We present a systematic recipe for translating ReLU approximation results to softmax Transformers1. Given a constructive ReLU approximator for a target, we construct an explicit softmax transformer with the same accuracy. The recipe applies to many common approximation targets and yields quantitative resource bounds beyond universal approximation statements. This matters because broad Universal Approximation Properties (UAP) still dominate Transformer approximation theory. For softmax Transformer, many universality results provide explicit constructions and quantitative resource bounds (e.g., parameters, depth, width...etc) [Yun et al., 2020, Kajitsuka and Sato, 2023, Takakura and Suzuki, 2023, Jiang and Li, 2024, Hu et al., 2025,

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as model steering and unlearning, it is essential to understand their guarantees, or lack thereof. In this work, we present a unified theoretical framework for unsupervised concept extraction, in which we frame the task of concept extraction as identifying a generative model. We present a general meta-theorem for identifiability, which reduces the problem of establishing identifiability guarantees to the problem of characterizing the intersection of two sets. As we demonstrate on a range of widely-used approaches, this meta-theorem substantially simplifies the task of proving such guarantees, thus paving the way for the development of new, principled approaches for concept extraction.

Whether or not a country is at war, or experiencing escalating or deescalating levels of conflict, has massive ramifications on a country's national and foreign policy. Given a country's history of conflict, or lack thereof, future predictions about the war-status of a country are valuable information. In this paper, we present the use of conformal prediction on temporally-dependent data to obtain prediction sets of possible future conflict state-sequences. More specifically, we compare the results of conformal prediction to a likelihood-based prediction strategy when the data are assumed to come from a discrete-state Markov process. A point-prediction may not supply sufficient information because the penalty for a wrong prediction is extreme, and so we consider a machine learning alternative that gives valid uncertainty quantification and is robust to model misspecification. In the data analysis, we present real forecasts of conflict dynamics across multiple countries. Lastly, we comment on the possible limitations of existing approaches for applying conformal prediction to Markovian data, where the exchangeability assumption is violated.