Text-to-Image (T2I) models often suffer from issues such as semantic leakage, incorrect feature binding, and omissions of key concepts in the generated image. This work studies these phenomena by looking into the role of information flow between textual token representations. To this end, we generate images by applying the diffusion component on a subset of contextual token representations in a given prompt and observe several interesting phenomena. First, in many cases, a word or multiword expression is fully represented by one or two tokens, while other tokens are redundant. For example, in "San Francisco's Golden Gate Bridge", the token "gate" alone captures the full expression. We demonstrate the redundancy of these tokens by removing them after textual encoding and generating an image from the resulting representation. Surprisingly, we find that this process not only maintains image generation performance but also reduces errors by 21\% compared to standard generation. We then show that information can also flow between different expressions in a sentence, which often leads to semantic leakage. Based on this observation, we propose a simple, training-free method to mitigate semantic leakage: replacing the leaked item's representation after the textual encoding with its uncontextualized representation. Remarkably, this simple approach reduces semantic leakage by 85\%. Overall, our work provides a comprehensive analysis of information flow across textual tokens in T2I models, offering both novel insights and practical benefits.

We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple diverse videos about real-world events, such as natural disasters or political elections. Videos are intuitive sources for retrieval-augmented generation (RAG), but most contemporary RAG workflows focus heavily on text and existing methods for video-based summarization focus on low-level scene understanding rather than high-level event semantics. To close this gap, we introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims, facilitating the integration of video into RAG pipelines and enabling the creation of in-depth content that is grounded in multimodal sources. We further propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos. CAG leverages an iterative interaction between an r1-style reasoning model and a VideoLLM to draw higher level inferences about the target event than is possible with VideoLLMs alone, which fixate on low-level visual features. We benchmark state-of-the-art VideoLLMs and CAG in both oracle retrieval and RAG settings and find that CAG consistently outperforms alternative methods, while suggesting intriguing avenues for future work.

Machine learning (ML) is becoming increasingly popular in meteorological decision-making. Although the literature on explainable artificial intelligence (XAI) is growing steadily, user-centered XAI studies have not extend to this domain yet. This study defines three requirements for explanations of black-box models in meteorology through user studies: statistical model performance for different rainfall scenarios to identify model bias, model reasoning, and the confidence of model outputs. Appropriate XAI methods are mapped to each requirement, and the generated explanations are tested quantitatively and qualitatively. An XAI interface system is designed based on user feedback. The results indicate that the explanations increase decision utility and user trust. Users prefer intuitive explanations over those based on XAI algorithms even for potentially easy-to-recognize examples. These findings can provide evidence for future research on user-centered XAI algorithms, as well as a basis to improve the usability of AI systems in practice.

Covariates play an indispensable role in practical time series forecasting, offering rich context from the past and sometimes extending into the future. However, their availability varies depending on the scenario, and situations often involve multiple target variables simultaneously. Moreover, the cross-variate dependencies between them are multi-granular, with some covariates having a short-term impact on target variables and others showing long-term correlations. This heterogeneity and the intricate dependencies arising in covariate-informed forecasting present significant challenges to existing deep models. To address these issues, we propose CITRAS, a patch-based Transformer that flexibly leverages multiple targets and covariates covering both the past and the future forecasting horizon. While preserving the strong autoregressive capabilities of the canonical Transformer, CITRAS introduces two novel mechanisms in patch-wise cross-variate attention: Key-Value (KV) Shift and Attention Score Smoothing. KV Shift seamlessly incorporates future known covariates into the forecasting of target variables based on their concurrent dependencies. Additionally, Attention Score Smoothing transforms locally accurate patch-wise cross-variate dependencies into global variate-level dependencies by smoothing the past series of attention scores. Experimentally, CITRAS achieves state-of-the-art performance in both covariate-informed and multivariate forecasting, demonstrating its versatile ability to leverage cross-variate dependency for improved forecasting accuracy.

This study systematically analyzes geopolitical bias across 11 prominent Large Language Models (LLMs) by examining their responses to seven critical topics in U.S.-China relations. Utilizing a bilingual (English and Chinese) and dual-framing (affirmative and reverse) methodology, we generated 19,712 prompts designed to detect ideological leanings in model outputs. Responses were quantitatively assessed on a normalized scale from -2 (strongly Pro-China) to +2 (strongly Pro-U.S.) and categorized according to stance, neutrality, and refusal rates. The findings demonstrate significant and consistent ideological alignments correlated with the LLMs' geographic origins; U.S.-based models predominantly favored Pro-U.S. stances, while Chinese-origin models exhibited pronounced Pro-China biases. Notably, language and prompt framing substantially influenced model responses, with several LLMs exhibiting stance reversals based on prompt polarity or linguistic context. Additionally, we introduced comprehensive metrics to evaluate response consistency across languages and framing conditions, identifying variability and vulnerabilities in model behaviors. These results offer practical insights that can guide organizations and individuals in selecting LLMs best aligned with their operational priorities and geopolitical considerations, underscoring the importance of careful model evaluation in politically sensitive applications. Furthermore, the research highlights specific prompt structures and linguistic variations that can strategically trigger distinct responses from models, revealing methods for effectively navigating and influencing LLM outputs.

Most operational climate services providers base their seasonal predictions on initialised general circulation models (GCMs) or statistical techniques that fit past observations. GCMs require substantial computational resources, which limits their capacity. In contrast, statistical methods often lack robustness due to short historical records. Recent works propose machine learning methods trained on climate model output, leveraging larger sample sizes and simulated scenarios. Yet, many of these studies focus on prediction tasks that might be restricted in spatial extent or temporal coverage, opening a gap with existing operational predictions. Thus, the present study evaluates the effectiveness of a methodology that combines variational inference with transformer models to predict fields of seasonal anomalies. The predictions cover all four seasons and are initialised one month before the start of each season. The model was trained on climate model output from CMIP6 and tested using ERA5 reanalysis data. We analyse the method's performance in predicting interannual anomalies beyond the climate change-induced trend. We also test the proposed methodology in a regional context with a use case focused on Europe. While climate change trends dominate the skill of temperature predictions, the method presents additional skill over the climatological forecast in regions influenced by known teleconnections. We reach similar conclusions based on the validation of precipitation predictions. Despite underperforming SEAS5 in most tropics, our model offers added value in numerous extratropical inland regions. This work demonstrates the effectiveness of training generative models on climate model output for seasonal predictions, providing skilful predictions beyond the induced climate change trend at time scales and lead times relevant for user applications.

The scientists didn't have high expectations when they asked their AI model to complete the poem. "He saw a carrot and had to grab it," they prompted the model. "His hunger was like a starving rabbit," it replied. The rhyming couplet wasn't going to win any poetry awards. But when the scientists at AI company Anthropic inspected the records of the model's neural network, they were surprised by what they found.

It's no secret that large language models work in mysterious ways. Few--if any--mass-market technologies have ever been so little understood. That makes figuring out what makes them tick one of the biggest open challenges in science. Shedding some light on how these models work would expose their weaknesses, revealing why they make stuff up and can be tricked into going off the rails. It would help resolve deep disputes about exactly what these models can and can't do.

Email: zhaoyuxin@hrbeu.edu.cn ( Y.Z.); szhang@ouc.edu.cn ( S.Z.) Abstract: El Niñ o - Southern Oscillation (ENSO) exerts global climate and societal impacts, but real - time prediction with lead times beyond one year remains challenging. Dynamical models suffer from large biases and uncertainties, while deep learning struggles with in terpretability and multi - scale dynamics. Here, we introduce PTSTnet, an interpretable model that unifies dynamical processes and cross - scale spatiotemporal learning in an innovative neural - network framework with physics - encoding learning. PTSTnet produces interpretable predictions significantly outperforming state - of - the - art benchmarks with lead times beyond 24 months, providing physical insights into error propagation in ocean - atmosphere interactions. PTSTnet learns feature representations with physical co nsistency from sparse data to tackle inherent multi - scale and multi - physics challenges underlying ocean - atmosphere processes, thereby inherently enhancing long - term prediction skill. Our successful realizations mark substantial steps forward in interpretab le insights into innovative neural ocean modelling . 2 Introduction The El Niño Southern Oscillation (ENSO) represents the main source of interannual variability in the global climate system, and the ability to predict large - scale climate variability and its impacts on global social and environmental systems is highly depe ndent on the quality of ENSO predictions ( 1 - 5) . With significant advances in ENSO observations and process understanding, considerable progress has been made in associated modelling and prediction in recent decades ( 6 - 10) .

Almost all textbooks to be used by first- and second-year high school students in Japan from fiscal 2026 will include quick response (QR) codes that link to websites with video and audio learning aid materials, sources said Tuesday. The education ministry said the same day that a total of 253 textbooks in 13 subjects have passed the second screenings under the current curriculum guidelines. In response to the rapid progress of digitalization, many of the textbooks include descriptions on information ethics and generative artificial intelligence. The average number of pages per textbook in 11 commonly taught subjects came to 321, slightly up from the previous screenings in 2021. All geography-history and civics textbooks take up the Northern Territories, which are effectively controlled by Russia; Takeshima, the Sea of Japan islets controlled by South Korea; and the Japanese-administered Senkaku Islands, which are also claimed by China.