The Self-Organising Map algorithm is a well-known approach for unsupervised learning, designed to distill a high-dimensional dataset into a more manageable, typically two-dimensional, representation. Imagine a dataset full of p measured variables across n observations. A Self-Organising Map elegantly organises similar observations into groups and visually displays them on a map. This model, also known as Kohonen maps or Kohonen networks, has been introduced by Teuvo Kohonen [Koh82, Koh97]. Unlike conventional neural networks, which rely on error correction, SOM training relies on competitive principles. Kohonen drew inspiration from biological paradigms, in particular the neural models [MP69] and Alan Turing's pioneering theories of morphogenesis [Tur52]. Basically, self-organising maps serve as powerful tools for dissecting and visualising complex data landscapes, facilitating a deeper understanding of the intricate structures and relationships that permeate multidimensional datasets. Self-organising maps, like most artificial neural network architectures, operate in two distinct modes: training and mapping.

The human brain is a complex and highly dynamic system, and our current knowledge of its functional mechanism is still very limited. Fortunately, with functional magnetic resonance imaging (fMRI), we can observe blood oxygen level-dependent (BOLD) changes, reflecting neural activity, to infer brain states and dynamics. In this paper, we ask the question of whether the brain states rep-resented by the regional brain fMRI can be predicted. Due to the success of self-attention and the transformer architecture in sequential auto-regression problems (e.g., language modelling or music generation), we explore the possi-bility of the use of transformers to predict human brain resting states based on the large-scale high-quality fMRI data from the human connectome project (HCP). Current results have shown that our model can accurately predict the brain states up to 5.04s with the previous 21.6s. Furthermore, even though the prediction error accumulates for the prediction of a longer time period, the gen-erated fMRI brain states reflect the architecture of functional connectome. These promising initial results demonstrate the possibility of developing gen-erative models for fMRI data using self-attention that learns the functional or-ganization of the human brain. Our code is available at: https://github.com/syf0122/brain_state_pred.

Apple Intelligence was the big news at the company's Worldwide Developers Conference back in June. Apple made good on a modest first wave of features in October. But iOS 18.2 -- along with sibling OS upgrades for Mac and iPad -- will bring a meatier set of Apple Intelligence features to Apple's suite of devices, including Genmoji, Image Playground and ChatGPT integration. To check out Apple's new AI, you must have an eligible device and run the current iOS 18.1, iPadOS 18.1 or MacOS 15.1. Once approved, you'll receive a notification saying it's ready to activate on your device.

It took over 15 years and more than 1,000 remotely operated vehicle (ROV) expeditions, but researchers aboard the NOAA Ocean Exploration Trust's Nautilus finally spotted their research vessel's namesake in the wild. On December 3, operators of the ship's Hercules ROV located four specimens of Palau nautilus (Nautilus belauensis) during the Nautilus Exploration Program's ongoing, 17-day survey in the Palau National Marine Sanctuary. While the team recorded these particular examples swimming 220-to-375 meters (roughly 721-to-1,230 ft) below the Pacific Ocean's surface, the pelagic marine mollusk cephalopods can survive at depths approaching 2,500 feet. Their spiral-shelled bodies belong to one of Earth's oldest families of animals, with fossil records indicating the squid relatives have changed comparatively little even after nearly 500 million years. Although their sight is limited due to rudimentary eyes that lack solid lenses, nine known nautilus species instead rely heavily on their olfactory senses to find food and mates.

Accurate 3D mapping in endoscopy enables quantitative, holistic lesion characterization within the gastrointestinal (GI) tract, requiring reliable depth and pose estimation. However, endoscopy systems are monocular, and existing methods relying on synthetic datasets or complex models often lack generalizability in challenging endoscopic conditions. We propose a robust self-supervised monocular depth and pose estimation framework that incorporates a Generative Latent Bank and a Variational Autoencoder (VAE). The Generative Latent Bank leverages extensive depth scenes from natural images to condition the depth network, enhancing realism and robustness of depth predictions through latent feature priors. For pose estimation, we reformulate it within a VAE framework, treating pose transitions as latent variables to regularize scale, stabilize z-axis prominence, and improve x-y sensitivity. This dual refinement pipeline enables accurate depth and pose predictions, effectively addressing the GI tract's complex textures and lighting. Extensive evaluations on SimCol and EndoSLAM datasets confirm our framework's superior performance over published self-supervised methods in endoscopic depth and pose estimation.

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interactions. Recent advancements in generative models, such as Autoencoders, Generative Adversarial Networks, Diffusion Models, Large Language Models, and Sequence-to-Sequence Models, have significantly contributed to the development of this field. However, there is a notable lack of comprehensive reviews in this field. To address this problem, this paper aims to address this gap by providing a thorough and systematic overview of recent advancements in human emotion synthesis based on generative models. Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used. Then, the review covers the application of different generative models to emotion synthesis based on a variety of modalities, including facial images, speech, and text. It also examines mainstream evaluation metrics. Additionally, the review presents some major findings and suggests future research directions, providing a comprehensive understanding of the role of generative technology in the nuanced domain of emotion synthesis.

Recent advancements in video anomaly understanding (VAU) have opened the door to groundbreaking applications in various fields, such as traffic monitoring and industrial automation. While the current benchmarks in VAU predominantly emphasize the detection and localization of anomalies. Here, we endeavor to delve deeper into the practical aspects of VAU by addressing the essential questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we introduce a comprehensive benchmark for Exploring the Causation of Video Anomalies (ECVA). Our benchmark is meticulously designed, with each video accompanied by detailed human annotations. Specifically, each instance of our ECVA involves three sets of human annotations to indicate "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. Building upon this foundation, we propose a novel prompt-based methodology that serves as a baseline for tackling the intricate challenges posed by ECVA. We utilize "hard prompt" to guide the model to focus on the critical parts related to video anomaly segments, and "soft prompt" to establish temporal and spatial relationships within these anomaly segments. Furthermore, we propose AnomEval, a specialized evaluation metric crafted to align closely with human judgment criteria for ECVA. This metric leverages the unique features of the ECVA dataset to provide a more comprehensive and reliable assessment of various video large language models. We demonstrate the efficacy of our approach through rigorous experimental analysis and delineate possible avenues for further investigation into the comprehension of video anomaly causation.

Machine learning methods in gamma spectroscopy have the potential to provide accurate, real-time classification of unknown radioactive samples. However, obtaining sufficient experimental training data is often prohibitively expensive and time-consuming, and models trained solely on synthetic data can struggle to generalize to the unpredictable range of real-world operating scenarios. In this work, we pretrain a model using physically derived synthetic data and subsequently leverage transfer learning techniques to fine-tune the model for a specific target domain. This paradigm enables us to embed physical principles during the pretraining step, thus requiring less data from the target domain compared to classical machine learning methods. Results of this analysis indicate that fine-tuned models significantly outperform those trained exclusively on synthetic data or solely on target-domain data, particularly in the intermediate data regime (${\approx} 10^4$ training samples). This conclusion is consistent across four different machine learning architectures (MLP, CNN, Transformer, and LSTM) considered in this study. This research serves as proof of concept for applying transfer learning techniques to application scenarios where access to experimental data is limited.

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/. Corresponding authors: Yushun Dong (yd24f@fsu.edu) is with the Department of Computer Science, Florida State University; Yue Zhao (yzhao010@usc.edu) is with the Department of Computer Science, University of Southern California; Fred Gui (pgui@lsu.edu) is with the Department of Political Science, Louisiana State University; Catherine Chen (catherinechen@lsu.edu) is with the Manship School of Mass Communication and the Department of Political Science, Louisiana State University.

How to properly conduct human evaluations for text summarization is a longstanding challenge. The Pyramid human evaluation protocol, which assesses content selection by breaking the reference summary into sub-units and verifying their presence in the system summary, has been widely adopted. However, it suffers from a lack of systematicity in the definition and granularity of the sub-units. We address these problems by proposing QAPyramid, which decomposes each reference summary into finer-grained question-answer (QA) pairs according to the QA-SRL framework. We collect QA-SRL annotations for reference summaries from CNN/DM and evaluate 10 summarization systems, resulting in 8.9K QA-level annotations. We show that, compared to Pyramid, QAPyramid provides more systematic and fine-grained content selection evaluation while maintaining high inter-annotator agreement without needing expert annotations. Furthermore, we propose metrics that automate the evaluation pipeline and achieve higher correlations with QAPyramid than other widely adopted metrics, allowing future work to accurately and efficiently benchmark summarization systems.