Automated scoring (AS) systems used in large-scale assessment have traditionally used small statistical models that require a large quantity of hand-scored data to make accurate predictions, which can be time-consuming and costly. Generative Large Language Models are trained on many tasks and have shown impressive abilities to generalize to new tasks with little to no data. While these models require substantially more computational power to make predictions, they still require some fine-tuning to meet operational standards. Evidence suggests that these models can exceed human-human levels of agreement even when fine-tuned on small amounts of data. With this in mind, we propose a model distillation pipeline in which a large generative model, a Teacher, teaches a much smaller model, a Student. The Teacher, trained on a small subset of the training data, is used to provide scores on the remaining training data, which is then used to train the Student. We call the resulting dataset "Cyborg Data", as it combines human and machine-scored responses. Our findings show that Student models trained on "Cyborg Data" show performance comparable to training on the entire dataset, while only requiring 10% of the original hand-scored data.

Recent generative reasoning breakthroughs have transformed how large language models (LLMs) tackle complex problems by dynamically retrieving and refining information while generating coherent, multi-step thought processes. Techniques such as inference-time scaling, reinforcement learning, supervised fine-tuning, and distillation have been successfully applied to models like DeepSeek-R1, OpenAI's o1 & o3, GPT-4o, Qwen-32B, and various Llama variants, resulting in enhanced reasoning capabilities. In this paper, we provide a comprehensive analysis of the top 27 LLM models released between 2023 and 2025 (including models such as Mistral AI Small 3 24B, DeepSeek-R1, Search-o1, QwQ-32B, and phi-4). Then, we present an extensive overview of training methodologies that spans general training approaches, mixture-of-experts (MoE) and architectural innovations, retrieval-augmented generation (RAG), chain-of-thought and self-improvement techniques, as well as test-time compute scaling, distillation, and reinforcement learning (RL) methods. Finally, we discuss the key challenges in advancing LLM capabilities, including improving multi-step reasoning without human supervision, overcoming limitations in chained tasks, balancing structured prompts with flexibility, and enhancing long-context retrieval and external tool integration.

Rapid advancements in large language models (LLMs) have increased interest in deploying them on mobile devices for on-device AI applications. Mobile users interact differently with LLMs compared to desktop users, creating unique expectations and data biases. Current benchmark datasets primarily target at server and desktop environments, and there is a notable lack of extensive datasets specifically designed for mobile contexts. Additionally, mobile devices face strict limitations in storage and computing resources, constraining model size and capabilities, thus requiring optimized efficiency and prioritized knowledge. To address these challenges, we introduce Mobile-MMLU, a large-scale benchmark dataset tailored for mobile intelligence. It consists of 16,186 questions across 80 mobile-related fields, designed to evaluate LLM performance in realistic mobile scenarios. A challenging subset, Mobile-MMLU-Pro, provides advanced evaluation similar in size to MMLU-Pro but significantly more difficult than our standard full set. Both benchmarks use multiple-choice, order-invariant questions focused on practical mobile interactions, such as recipe suggestions, travel planning, and essential daily tasks. The dataset emphasizes critical mobile-specific metrics like inference latency, energy consumption, memory usage, and response quality, offering comprehensive insights into model performance under mobile constraints. Moreover, it prioritizes privacy and adaptability, assessing models' ability to perform on-device processing, maintain user privacy, and adapt to personalized usage patterns. Mobile-MMLU family offers a standardized framework for developing and comparing mobile-optimized LLMs, enabling advancements in productivity and decision-making within mobile computing environments. Our code and data are available at: https://github.com/VILA-Lab/Mobile-MMLU.

GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations Y upei Li, Qiyang Sun, Sunil Munthumoduku Krishna Murthy, Emran Alturki, and Bj orn W . Schuller Fellow, IEEE Abstract --Affective Computing (AC) is essential for advancing Artificial General Intelligence (AGI), with emotion recognition serving as a key component. However, human emotions are inherently dynamic, influenced not only by an individual's expressions but also by interactions with others, and single-modality approaches often fail to capture their full dynamics. Multimodal Emotion Recognition (MER) leverages multiple signals but traditionally relies on utterance-level analysis, overlooking the dynamic nature of emotions in conversations. Emotion Recognition in Conversation (ERC) addresses this limitation, yet existing methods struggle to align multimodal features and explain why emotions evolve within dialogues. T o bridge this gap, we propose GatedxLSTM, a novel speech-text multimodal ERC model that explicitly considers voice and transcripts of both the speaker and their conversational partner(s) to identify the most influential sentences driving emotional shifts. By integrating Contrastive Language-Audio Pretraining (CLAP) for improved cross-modal alignment and employing a gating mechanism to emphasise emotionally impactful utterances, GatedxLSTM enhances both interpretability and performance. Experiments on the IEMOCAP dataset demonstrate that GatedxLSTM achieves state-of-the-art (SOT A) performance among open-source methods in four-class emotion classification. These results validate its effectiveness for ERC applications and provide an interpretability analysis from a psychological perspective. I NTRODUCTION Artificial General Intelligence (AGI) represents a key future direction in AI development, with Affective Computing (AC) playing a crucial role in enhancing AGI's ability to interact effectively with humans. Sunil Munthumoduku Krishna Murthy is with CHI - Chair of Health Informatics, MRI, Technical University of Munich, Germany (e-mail: sunil.munthumoduku@tum.de). Bj orn W . Schuller is with GLAM, Department of Computing, Imperial College London, UK; CHI - Chair of Health Informatics, Technical University of Munich, Germany; relAI - the Konrad Zuse School of Excellence in Reliable AI, Munich, Germany; MDSI - Munich Data Science Institute, Munich, Germany; and MCML - Munich Center for Machine Learning, Munich, Germany (e-mail: schuller@tum.de). Y upei Li and Qiyang Sun contributed equally to this work.

Graphical User Interface (GUI) agents are autonomous systems that interpret and generate actions, enabling intelligent user assistance and automation. Effective training of these agent presents unique challenges, such as sparsity in supervision signals, scalability for large datasets, and the need for nuanced user understanding. We propose stateful screen schema, an efficient representation of GUI interactions that captures key user actions and intentions over time. Building on this foundation, we introduce ScreenLLM, a set of multimodal large language models (MLLMs) tailored for advanced UI understanding and action prediction. Extensive experiments on both open-source and proprietary models show that ScreenLLM accurately models user behavior and predicts actions. Our work lays the foundation for scalable, robust, and intelligent GUI agents that enhance user interaction in diverse software environments.

Due to their versatility, concept maps are used in various educational settings and serve as tools that enable educators to comprehend students' knowledge construction. An essential component for analyzing a concept map is its structure, which can be categorized into three distinct types: spoke, network, and chain. Understanding the predominant structure in a map offers insights into the student's depth of comprehension of the subject. Therefore, this study examined 317 distinct concept map structures, classifying them into one of the three types, and used statistical and descriptive information from the maps to train multiclass classification models. As a result, we achieved an 86\% accuracy in classification using a Decision Tree. This promising outcome can be employed in concept map assessment systems to provide real-time feedback to the student.

This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA), with a focus on implicit aspect extraction in a novel domain. Using a synthetic sports feedback dataset, we evaluate open-weight LLMs' ability to extract aspect-polarity pairs and propose a metric to facilitate the evaluation of aspect extraction with generative models. Our findings highlight both the potential and limitations of LLMs in the ABSA task.

In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often struggle to capture and represent the essential characteristics of evolving visual concepts, hindering their applicability to dynamic graphics tasks. In this paper, we propose Ancestral Mamba, a novel approach that integrates online prototype learning into a selective discriminant space model for efficient and robust online continual learning. The key components of our approach include Ancestral Prototype Adaptation (AP A), which continuously refines and builds upon learned visual prototypes, and Mamba Feedback (MF), which provides targeted feedback to adapt to challenging visual patterns. AP A enables the model to continuously adapt its prototypes, building upon ancestral knowledge to tackle new challenges, while MF acts as a targeted feedback mechanism, focusing on challenging classes and refining their representations. Extensive experiments on graphics-oriented datasets, such as CIF AR-10 and CIF AR-100, demonstrate the superior performance of Ancestral Mamba compared to state-of-the-art baselines, achieving significant improvements in accuracy and forgetting mitigation. 1. Introduction Online continual learning (OCL) aims to learn continuously from a non-stationary data stream while adapting to new data and mitigating catastrophic forgetting [1, 11, 17, 21]. Recently, online prototype Learning (OnPro) [22] has attracted a lot of attention with its brilliant performance in the OCL field. This paradigm holds immense potential for real-world applications, particularly in the realm of computer graphics, where the ability to process and adapt to evolving visual patterns, shapes, and colours is of paramount importance. Catastrophic forgetting [7, 22, 23, 25] stands as a major hurdle in online continual learning, akin to a visual artist abruptly losing previously acquired skills when adapting to new styles.

Education materials for K-12 students often consist of multiple modalities, such as text and images, posing challenges for models to fully understand nuanced information in these materials. In this paper, we propose a unified language and vision assistant UniEDU designed for various educational applications, including knowledge recommendation, knowledge tracing, time cost prediction, and user answer prediction, all within a single model. Unlike conventional task-specific models, UniEDU offers a unified solution that excels across multiple educational tasks while maintaining strong generalization capabilities. Its adaptability makes it well-suited for real-world deployment in diverse learning environments. Furthermore, UniEDU is optimized for industry-scale deployment by significantly reducing computational overhead-achieving approximately a 300\% increase in efficiency-while maintaining competitive performance with minimal degradation compared to fully fine-tuned models. This work represents a significant step toward creating versatile AI systems tailored to the evolving demands of education.

Semiconductor devices, especially MOSFETs (Metal-oxide-semiconductor field-effect transistor), are crucial in power electronics, but their reliability is affected by aging processes influenced by cycling and temperature. The primary aging mechanism in discrete semiconductors and power modules is the bond wire lift-off, caused by crack growth due to thermal fatigue. The process is empirically characterized by exponential growth and an abrupt end of life, making long-term aging forecasts challenging. This research presents a comprehensive comparative assessment of different forecasting methods for MOSFET failure forecasting applications. Classical tracking, statistical forecasting and Neural Network (NN) based forecasting models are implemented along with novel Temporal Fusion Transformers (TFTs). A comprehensive comparison is performed assessing their MOSFET ageing forecasting ability for different forecasting horizons. For short-term predictions, all algorithms result in acceptable results, with the best results produced by classical NN forecasting models at the expense of higher computations. For long-term forecasting, only the TFT is able to produce valid outcomes owing to the ability to integrate covariates from the expected future conditions. Additionally, TFT attention points identify key ageing turning points, which indicate new failure modes or accelerated ageing phases.