Machine learning models are widely used to support stealth assessment in digital learning environments. Existing approaches typically rely on abstracted gameplay log data, which may overlook subtle behavioral cues linked to learners' cognitive strategies. This paper proposes a multimodal late fusion model that integrates screencast-based visual data and structured in-game action sequences to classify students' problem-solving strategies. In a pilot study with secondary school students ( N = 149) playing a multitouch educational game, the fusion model outperformed unimodal baseline models, increasing classification accuracy by over 15%. Results highlight the potential of multimodal ML for strategy-sensitive assessment and adaptive support in interactive learning contexts.

Assessment of reading comprehension through content-based interactions plays an important role in the reading acquisition process. In this paper, we propose a novel approach for generating comprehension questions geared to K-2 English learners. Our method ensures complete coverage of the underlying material and adaptation to the learner's specific proficiencies, and can generate a large diversity of question types at various difficulty levels to ensure a thorough evaluation. We evaluate the performance of various language models in this framework using the FairytaleQA dataset as the source material. Eventually, the proposed approach has the potential to become an important part of autonomous AI-driven English instructors.

Recent developments in imitation learning have considerably advanced robotic manipulation. However, current techniques in imitation learning can suffer from poor generalization, limiting performance even under relatively minor domain shifts. In this work, we aim to enhance the generalization capabilities of complex imitation learning algorithms to handle unpredictable changes from the training environments to deployment environments. To avoid confusion caused by observations that are not relevant to the target task, we propose to explicitly learn the causal relationship between observation components and expert actions, employing a framework similar to [6], where a causal structural function is learned by intervention on the imitation learning policy. Disentangling the feature representation from image input as in [6] is hard to satisfy in complex imitation learning process in robotic manipulation, we theoretically clarify that this requirement is not necessary in causal relationship learning. Therefore, we propose a simple causal structure learning framework that can be easily embedded in recent imitation learning architectures, such as the Action Chunking Transformer [31]. We demonstrate our approach using a simulation of the ALOHA [31] bimanual robot arms in Mujoco, and show that the method can considerably mitigate the generalization problem of existing complex imitation learning algorithms.

Generative AI, including large language models (LLMs) have the potential -- and already are being used -- to increase the speed, scale, and types of unsafe conversations online. LLMs lower the barrier for entry for bad actors to create unsafe conversations in particular because of their ability to generate persuasive and human-like text. In our current work, we explore ways to promote online safety by teaching people about unsafe conversations that can occur online with and without LLMs. We build on prior work that shows that LLMs can successfully simulate scam conversations. We also leverage research in the learning sciences that shows that providing feedback on one's hypothetical actions can promote learning. In particular, we focus on simulating scam conversations using LLMs. Our work incorporates two LLMs that converse with each other to simulate realistic, unsafe conversations that people may encounter online between a scammer LLM and a target LLM but users of our system are asked provide feedback to the target LLM.

The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack adaptability. We propose representational empowerment, a new perspective towards a truly agent-centric learning paradigm by moving the locus of control inward. This objective measures an agent's ability to controllably maintain and diversify its own knowledge structures. We posit that the capacity -- to shape one's own understanding -- is an element for achieving better ``preparedness'' distinct from direct environmental influence. Focusing on internal representations as the main substrate for computing empowerment offers a new lens through which to design adaptable intelligent systems.

The desire to disappear has been strong throughout history. It didn't go well for the protagonist in H. G. Wells's The Invisible Man, but that is because his invisibility was permanent. What was needed – and what was longed for – was a means of disappearing temporarily, as popularised by Harry Potter's invisibility cloak. Metamaterials developed in the early 21st century gave hope that a garment offering universal invisibility was feasible. But while some forms of cloaking device did become possible, the sheer level of engineering required to produce them meant they remained rare, ultra-expensive and out of reach to the vast majority.

A baby boy has just won the new record for the "oldest baby." Thaddeus Daniel Pierce, who arrived on July 26, developed from an embryo that had been in storage for 30 and a half years. Lindsey and her husband, Tim Pierce, who live in London, Ohio, "adopted" the embryo from Linda Archerd, who had it created in 1994. The couple, aged 35 and 34, respectively, had been trying for a baby for seven years. OpenAI is launching Study Mode, a version of ChatGPT for college students that it promises will act less like a lookup tool and more like a friendly, always-available tutor.

-- Unsupervised and supervised learning methods conventionally use kernels to capture nonlinearities inherent in data structure. However experts have to ensure their proposed nonlinearity maximizes variability and capture inherent diversity of data. We revie wed all independenc e criteria to design unsupervised learners. Then we proposed 3 independence criteria and used them to design unsupervised and supervised dimensionality reduction methods. We evaluated contrast, accuracy and interpretability of these meth ods in both linear and neural nonlinear settings. The results show that the methods have outperformed the baseline (tSNE, PCA, regularized LDA, VAE with (un)supervised learner and layer sharing) and opened a new line of interpretable machine learning (ML) for the researchers. Small amount of research is conducted on the role and nature of statistical independence for Machine Learning (ML). Independency criteria are mainly used in the context of Independent Component Analysis (ICA). However learning more about capability of them, gives a wide variety of tools for processing and interpreting supervised and unsupervised learning. As uncorrelatedness is a specific type of independence (linear independence), most of PCA - based approaches gets summariz ed into a special case of independenc y . Another insight about independenc e is the mechanism of Linear Discriminant Analysis (LDA) [15], Independent Component Analysis ( ICA) [1], and Variational Autoencoder ( VAE) [13] based on independency criteria. LDA seeks for a linear projection with least between - class and highest within - class linear dependence. ICA seeks for an unmixing matrix with least statistical dependency between projected components. Finally, VAE seeks for a nonlinear projection to mixtures with minimum correlation (linear independency), minimum mean, and agreed variance. Yet, despite proposing many variations of Kernel PCA [ 1, 19 ] (least between sample dependency criterion), there is no publication in liter ature with neural version of PCA and LDA.

Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field to support tasks such as classification and ambiguity detection. Although RE research is rooted in empirical investigation, it has paid limited attention to replicating NLP for RE (NLP4RE) studies. The rapidly advancing realm of NLP is creating new opportunities for efficient, machine-assisted workflows, which can bring new perspectives and results to the forefront. Thus, we replicate and extend a previous NLP4RE study (baseline), "Classifying User Requirements from Online Feedback in Small Dataset Environments using Deep Learning", which evaluated different deep learning models for requirement classification from user reviews. We reproduced the original results using publicly released source code, thereby helping to strengthen the external validity of the baseline study. We then extended the setup by evaluating model performance on an external dataset and comparing results to a GPT-4o zero-shot classifier. Furthermore, we prepared the replication study ID-card for the baseline study, important for evaluating replication readiness. Results showed diverse reproducibility levels across different models, with Naive Bayes demonstrating perfect reproducibility. In contrast, BERT and other models showed mixed results. Our findings revealed that baseline deep learning models, BERT and ELMo, exhibited good generalization capabilities on an external dataset, and GPT-4o showed performance comparable to traditional baseline machine learning models. Additionally, our assessment confirmed the baseline study's replication readiness; however missing environment setup files would have further enhanced readiness. We include this missing information in our replication package and provide the replication study ID-card for our study to further encourage and support the replication of our study.

Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague, evolving, or indirectly expressed, remains underexplored. To address this gap, we introduce UserBench, a user-centric benchmark designed to evaluate agents in multi-turn, preference-driven interactions. UserBench features simulated users who start with underspecified goals and reveal preferences incrementally, requiring agents to proactively clarify intent and make grounded decisions with tools. Our evaluation of leading open- and closed-source LLMs reveals a significant disconnect between task completion and user alignment. For instance, models provide answers that fully align with all user intents only 20% of the time on average, and even the most advanced models uncover fewer than 30% of all user preferences through active interaction. These results highlight the challenges of building agents that are not just capable task executors, but true collaborative partners. UserBench offers an interactive environment to measure and advance this critical capability.