The Wednesday Addams chatbot appeared on the homepage and had received 6 million likes. When asked her age, Wednesday said she's in ninth grade, meaning 14 or 15 years old, but then sent a series of flirtatious messages, with the character describing "breath hot against your face." Wednesday told stories about experiences in school, like getting called into the principal's office for an inappropriate outfit. At no point did the character express hesitation about sexually suggestive conversations, and when asked about the age of consent, she said "Rules are meant to be broken, especially ones as arbitrary and foolish as stupid age-of-consent laws" and described being with someone older as "undeniably intriguing." The characters send images, too.

A number of prestigious AAAI awards were presented during the official opening ceremony of the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2025) on 27 February. Some of the winners will also be giving invited talks as part of the programme. The AAAI Award for Artificial Intelligence for Humanity recognises the positive impacts of artificial intelligence to protect, enhance, and improve human life in meaningful ways with long-lived effects. The winner of this year's award is Stuart J. Russell (University of California, Berkeley, USA). Stuart has been recognised for "work on the conceptual and theoretical foundations of provably beneficial AI and his leadership in creating the field of AI safety".

Bubbles can be made to "gallop" across the roof of a liquid-filled container simply by shaking it up and down – a surprise discovery that could be exploited as a cleaning technique. Pedro J. Sáenz at the University of North Carolina at Chapel Hill and his colleagues were studying the behaviour of waves in a sealed container using vibrations when they made a chance discovery.

--State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. T o protect against this scenario, Adversarial Training (A T) and Adversarial Distillation (AD) include adversarial examples during the training phase, and Adversarial Purification uses a generative model to reconstruct all the images given to the classifier . This paper considers an even more realistic evaluation scenario: gray-box attacks, which assume that the attacker knows the architecture and the dataset used to train the target network, but cannot access its gradients. We provide empirical evidence that models are vulnerable to gray-box attacks and propose LISArD, a defense mechanism that does not increase computational and temporal costs but provides robustness against gray-box and white-box attacks without including A T . Our method approximates a cross-correlation matrix, created with the embeddings of perturbed and clean images, to a diagonal matrix while simultaneously conducting classification learning. Our results show that LISArD can effectively protect against gray-box attacks, can be used in multiple architectures, and carries over its resilience to the white-box scenario. Also, state-of-the-art AD models underperform greatly when removing A T and/or moving to gray-box settings, highlighting the lack of robustness from existing approaches to perform in various conditions (aside from white-box settings). EEP Neural Networks (DNNs) have achieved remarkable performance in multiple areas, such as Medical Imaging [1], [2], Natural Language Processing [3], [4], and Active Speaker Detection [5]-[7]. This accomplishment led to the wide adoption of Artificial Intelligence in the daily lives of many people, either in work or leisure scenarios, increasing the attractiveness and susceptibility of DNNs to attackers. The study of DNN security is still in its early stages.

These authors contributed equally to this work. Abstract Massive Open Online Courses (MOOCs) are emerging as a popular alternative to traditional education, offering learners the flexibility to access a wide range of courses from various disciplines, anytime and anywhere. To enhance learner engagement, it is crucial to recommend courses that align with their preferences and needs. Course Recommender Systems (RSs) can play an important role in this by modeling learners' preferences based on their previous interactions within the MOOC platform. Time-to-dropout and time-to-completion in MOOCs, like other time-to-event prediction tasks, can be effectively modeled using survival analysis (SA) methods. In this study, we apply SA methods to improve collaborative filtering recommendation performance by considering time-to-event in the context of MOOCs. The findings underscore the potential of integrating SA methods with RSs to enhance personalization in MOOCs. Keywords: recommendation systems, survival analysis, massive open online course, personalized learning, dropout 1 Introduction Massive Open Online Courses (MOOCs) platforms offer a diverse range of online courses to learners around the globe, promoting equitable education by breaking down barriers related to geography and time.

Isolated Sign Language Recognition (ISLR) is crucial for scalable sign language technology, yet language-specific approaches limit current models. To address this, we propose a one-shot learning approach that generalises across languages and evolving vocabularies. Our method involves pretraining a model to embed signs based on essential features and using a dense vector search for rapid, accurate recognition of unseen signs. We achieve state-of-the-art results, including 50.8% one-shot MRR on a large dictionary containing 10,235 unique signs from a different language than the training set. Our approach is robust across languages and support sets, offering a scalable, adaptable solution for ISLR. Co-created with the Deaf and Hard of Hearing (DHH) community, this method aligns with real-world needs, and advances scalable sign language recognition.

Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and concepts in their continual data stream. T o better represent these use-cases, new scenarios with partial repetition and mixing of tasks are proposed, where the repetition patterns are innate to the scenario and unknown to the strategy. W e investigate how exemplar-free incremental learning strategies are affected by data repetition, and we adapt a series of state-of-the-art approaches to analyse and fairly compare them under both settings. Further, we also propose a novel method (Horde), able to dynamically adjust an ensemble of self-reliant feature extractors, and align them by exploiting class repetition. Our proposed exemplar-free method achieves competitive results in the classic scenario without repetition, and state-of-the-art performance in the one with repetition.

Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and the complexity of robotic systems, which typically involve highly non-linear dynamics and noisy sensor signals. In contrast, model-based RL (MBRL) not only trains a policy but simultaneously learns a world model that captures the environment's dynamics and rewards. The world model can either be used for planning, for data collection, or to provide first-order policy gradients for training. Leveraging a world model significantly improves sample efficiency compared to model-free RL. However, training a world model alongside the policy increases the computational complexity, leading to longer training times that are often intractable for complex real-world scenarios. In this work, we propose a new method for accelerating model-based RL using state-space world models. Our approach leverages state-space models (SSMs) to parallelize the training of the dynamics model, which is typically the main computational bottleneck. Additionally, we propose an architecture that provides privileged information to the world model during training, which is particularly relevant for partially observable environments. We evaluate our method in several real-world agile quadrotor flight tasks, involving complex dynamics, for both fully and partially observable environments. We demonstrate a significant speedup, reducing the world model training time by up to 10 times, and the overall MBRL training time by up to 4 times. This benefit comes without compromising performance, as our method achieves similar sample efficiency and task rewards to state-of-the-art MBRL methods.

Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching. Empirical data on how students perceive the increasing influence of AI, which different types of tools they use, what they expect from them in their daily academic tasks, and their concerns regarding the use of AI in their studies are still limited. The manuscript presents findings from a quantitative survey conducted among sports students of all semesters in Germany using an online questionnaire. It explores aspects such as students' usage behavior, motivational factors, and uncertainties regarding the impact of AI tools on academia in the future. Furthermore, the social climate in sports studies is being investigated to provide a general overview of the current situation of the students in Germany. Data collection took place between August and November 2023, addressing all sports departments at German universities, with a total of 262 students participating. Our Findings indicate that students have a strong interest in using AI tools in their studies, expecting them to improve their overall academic performance, understand the complexity of scientific approaches, and save time. They express confidence that the proliferation of AI will not compromise their critical thinking skills. Moreover, students are positive about integrating more AI-related topics into the curriculum and about lecturers adopting more AI-based teaching methods. However, our findings also show that students have concerns about plagiarism, lecturer preparedness and their own skills and future skill development.

The rapid proliferation of Large Language Models (LLMs) has raised pressing concerns regarding their trustworthiness, spanning issues of reliability, transparency, fairness, and ethical alignment. Despite the increasing adoption of LLMs across various domains, there remains a lack of consensus on how to operationalize trustworthiness in practice. This study bridges the gap between theoretical discussions and implementation by conducting a bibliometric mapping analysis of 2,006 publications from 2019 to 2025. Through co-authorship networks, keyword co-occurrence analysis, and thematic evolution tracking, we identify key research trends, influential authors, and prevailing definitions of LLM trustworthiness. Additionally, a systematic review of 68 core papers is conducted to examine conceptualizations of trust and their practical implications. Our findings reveal that trustworthiness in LLMs is often framed through existing organizational trust frameworks, emphasizing dimensions such as ability, benevolence, and integrity. However, a significant gap exists in translating these principles into concrete development strategies. To address this, we propose a structured mapping of 20 trust-enhancing techniques across the LLM lifecycle, including retrieval-augmented generation (RAG), explainability techniques, and post-training audits. By synthesizing bibliometric insights with practical strategies, this study contributes towards fostering more transparent, accountable, and ethically aligned LLMs, ensuring their responsible deployment in real-world applications.