Purpose: We investigated the utilization of privacy-preserving, locally-deployed, open-source Large Language Models (LLMs) to extract diagnostic information from free-text cardiovascular magnetic resonance (CMR) reports. Materials and Methods: We evaluated nine open-source LLMs on their ability to identify diagnoses and classify patients into various cardiac diagnostic categories based on descriptive findings in 109 clinical CMR reports. Performance was quantified using standard classification metrics including accuracy, precision, recall, and F1 score. We also employed confusion matrices to examine patterns of misclassification across models. Results: Most open-source LLMs demonstrated exceptional performance in classifying reports into different diagnostic categories. Google's Gemma2 model achieved the highest average F1 score of 0.98, followed by Qwen2.5:32B and DeepseekR1-32B with F1 scores of 0.96 and 0.95, respectively. All other evaluated models attained average scores above 0.93, with Mistral and DeepseekR1-7B being the only exceptions. The top four LLMs outperformed our board-certified cardiologist (F1 score of 0.94) across all evaluation metrics in analyzing CMR reports. Conclusion: Our findings demonstrate the feasibility of implementing open-source, privacy-preserving LLMs in clinical settings for automated analysis of imaging reports, enabling accurate, fast and resource-efficient diagnostic categorization.

In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by noisy correspondence learning (NCL). Such noise often stems from mismatched data pairs, which is a significant obstacle distinct from traditional noisy labels. This paper introduces Pseudo-Classification based Pseudo-Captioning (PC$^2$) framework to address this challenge. PC$^2$ offers a threefold strategy: firstly, it establishes an auxiliary "pseudo-classification" task that interprets captions as categorical labels, steering the model to learn image-text semantic similarity through a non-contrastive mechanism. Secondly, unlike prevailing margin-based techniques, capitalizing on PC$^2$'s pseudo-classification capability, we generate pseudo-captions to provide more informative and tangible supervision for each mismatched pair. Thirdly, the oscillation of pseudo-classification is borrowed to assistant the correction of correspondence. In addition to technical contributions, we develop a realistic NCL dataset called Noise of Web (NoW), which could be a new powerful NCL benchmark where noise exists naturally. Empirical evaluations of PC$^2$ showcase marked improvements over existing state-of-the-art robust cross-modal retrieval techniques on both simulated and realistic datasets with various NCL settings. The contributed dataset and source code are released at https://github.com/alipay/PC2-NoiseofWeb.

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.

Acute Kidney Injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series data has a negative impact on workload and study quality. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation. The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We defined a standardized data model in order to ensure reproducibility. Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels. This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.

Can we imagine a scenario in which the different anxieties aroused by George Romero's horror film Night of the Living Dead and Stanley Kubrick's sci-fi dystopia 2001: A Space Odyssey merge? How might a monster that combined our fear of becoming something less than human with our fear of increasingly "intelligent" machines appear to us and what might it say? There is one work – of both horror and science fiction – that imagines such a monster. Published almost exactly 150 years before Romero and Kubrick released their movies, it is a book in which physical deformity and technological mutiny coalesce, creating a monster that is both a zombie and AI, or something in between the two. A gothic fiction, it is also described by some literary historians as the first science-fiction novel.

We introduce a new open information extraction (OIE) benchmark for pre-trained language models (LM). Recent studies have demonstrated that pre-trained LMs, such as BERT and GPT, may store linguistic and relational knowledge. In particular, LMs are able to answer ``fill-in-the-blank'' questions when given a pre-defined relation category. Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs. We accomplish this by turning pre-trained LMs into zero-shot OIE systems. Surprisingly, pre-trained LMs are able to obtain competitive performance on both standard OIE datasets (CaRB and Re-OIE2016) and two new large-scale factual OIE datasets (TAC KBP-OIE and Wikidata-OIE) that we establish via distant supervision. For instance, the zero-shot pre-trained LMs outperform the F1 score of the state-of-the-art supervised OIE methods on our factual OIE datasets without needing to use any training sets. Our code and datasets are available at https://github.com/cgraywang/IELM

The problem with waiting for quantum computing to bring in the next wave of AI is that it's likely to arrive a lot slower than people would like. The next best options include increasing the speed of existing computers somehow -- but there's now an important added imperative: power-efficient systems that mean we don't burn up the planet while we get about conjuring the AI singularity into existence. Meanwhile, the speed of AI computation doubles every three or four months, meaning that standard semiconductor technologies are struggling to keep up. Several companies are now working on "photonics processing", which introduces light into the semiconductor realm which, for obvious "speed of light" reasons, literally speeds up the whole thing markedly. Salience Labs is an Oxford-based startup that thinks it has the answer, by combining an ultra-high-speed multi-chip processor that packages a photonics chip together with standard electronics.

Statistical models are inherently uncertain. Quantifying or at least upper-bounding their uncertainties is vital for safety-critical systems such as autonomous vehicles. While standard neural networks do not report this information, several approaches exist to integrate uncertainty estimates into them. Assessing the quality of these uncertainty estimates is not straightforward, as no direct ground truth labels are available. Instead, implicit statistical assessments are required. For regression, we propose to evaluate uncertainty realism -- a strict quality criterion -- with a Mahalanobis distance-based statistical test. An empirical evaluation reveals the need for uncertainty measures that are appropriate to upper-bound heavy-tailed empirical errors. Alongside, we transfer the variational U-Net classification architecture to standard supervised image-to-image tasks. We adopt it to the automotive domain and show that it significantly improves uncertainty realism compared to a plain encoder-decoder model.

In a recent nature perspective, international experts in the field of optical neural networks, optical deep learning and photonic computing have put their expertise together to review the path from pathbreaking optical neural networks and optical computing realizations in the past fifty years and how they advanced to photonic artificial intelligence applications. The team, which includes the physicist Prof. Cornelia Denz from the Institute of Applied Physics at the University of Münster, discusses also promises and challenges for future deep optics and photonics and its next-generation applications in knowledge representation, learning, planning and perception. Artificial intelligence – the intelligence demonstrated by machines – is a central topic in today's society. Ranging from autonomously operating cars over strategic game an optimization systems up to understanding human speech, they all have in common that they act as "intelligent agents" that perceive its environment and takes actions that maximize its chance of success or of achieving a certain goal. Many of these tasks require huge data set for learning or processing and thus at the same time fast and low-power execution.

This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner, requiring humans to create knowledge. Recent deep language models automatically acquire knowledge from large-scale corpora via pre-training. The stored knowledge has enabled the language models to improve downstream NLP tasks, e.g., answering questions, and writing code and articles. In this paper, we propose an unsupervised method to cast the knowledge contained within language models into KGs. We show that KGs are constructed with a single forward pass of the pre-trained language models (without fine-tuning) over the corpora. We demonstrate the quality of the constructed KGs by comparing to two KGs (Wikidata, TAC KBP) created by humans. Our KGs also provide open factual knowledge that is new in the existing KGs. Our code and KGs will be made publicly available.