Given the demand for responsible and trustworthy AI for education, this study evaluates symbolic, sub-symbolic, and neural-symbolic AI (NSAI) in terms of generalizability and interpretability. Our extensive experiments on balanced and imbalanced self-regulated learning datasets of Estonian primary school students predicting 7th-grade mathematics national test performance showed that symbolic and sub-symbolic methods performed well on balanced data but struggled to identify low performers in imbalanced datasets. Interestingly, symbolic and sub-symbolic methods emphasized different factors in their decision-making: symbolic approaches primarily relied on cognitive and motivational factors, while sub-symbolic methods focused more on cognitive aspects, learnt knowledge, and the demographic variable of gender -- yet both largely overlooked metacognitive factors. The NSAI method, on the other hand, showed advantages by: (i) being more generalizable across both classes -- even in imbalanced datasets -- as its symbolic knowledge component compensated for the underrepresented class; and (ii) relying on a more integrated set of factors in its decision-making, including motivation, (meta)cognition, and learnt knowledge, thus offering a comprehensive and theoretically grounded interpretability framework. These contrasting findings highlight the need for a holistic comparison of AI methods before drawing conclusions based solely on predictive performance. They also underscore the potential of hybrid, human-centred NSAI methods to address the limitations of other AI families and move us closer to responsible AI for education. Specifically, by enabling stakeholders to contribute to AI design, NSAI aligns learned patterns with theoretical constructs, incorporates factors like motivation and metacognition, and strengthens the trustworthiness and responsibility of educational data mining.

In contrast to the human ability to continuously acquire knowledge, agents struggle with the stability-plasticity dilemma in deep reinforcement learning (DRL), which refers to the trade-off between retaining existing skills (stability) and learning new knowledge (plasticity). Current methods focus on balancing these two aspects at the network level, lacking sufficient differentiation and fine-grained control of individual neurons. To overcome this limitation, we propose Neuron-level Balance between Stability and Plasticity (NBSP) method, by taking inspiration from the observation that specific neurons are strongly relevant to task-relevant skills. Specifically, NBSP first (1) defines and identifies RL skill neurons that are crucial for knowledge retention through a goal-oriented method, and then (2) introduces a framework by employing gradient masking and experience replay techniques targeting these neurons to preserve the encoded existing skills while enabling adaptation to new tasks. Numerous experimental results on the Meta-World and Atari benchmarks demonstrate that NBSP significantly outperforms existing approaches in balancing stability and plasticity.

In the era of Large Language Models (LLMs), establishing effective evaluation methods and standards for diverse human-AI interaction systems is increasingly challenging. To encourage more transparent documentation and facilitate discussion on human-AI system evaluation design options, we present an evaluation card SPHERE, which encompasses five key dimensions: 1) What is being evaluated?; 2) How is the evaluation conducted?; 3) Who is participating in the evaluation?; 4) When is evaluation conducted?; 5) How is evaluation validated? We conduct a review of 39 human-AI systems using SPHERE, outlining current evaluation practices and areas for improvement. We provide three recommendations for improving the validity and rigor of evaluation practices.

'The Big Weekend Show' co-hosts discuss Tinder user traffic peaking during'Dating Sunday.' A judge has dismissed kidnapping and conspiracy charges filed against five Massachusetts college students accused of luring a man to their campus in a "Catch a Predator"-style scheme using a dating app. A Worcester District Court judge dismissed the charges against Kelsey Brainard, Isabella Trudeau, Joaquin Smith, Kevin Carroll and Easton Randall on Tuesday. The decision came after lawyers for the teenage Assumption University students claimed prosecutors lacked probable cause and filed motions to dismiss last month. Information regarding the status of a sixth student, charged as a juvenile, was not immediately available.

The advancement of Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs) and large vision-language models (LVLMs). However, a rigorous evaluation framework for video CoT reasoning remains absent. Current video benchmarks fail to adequately assess the reasoning process and expose whether failures stem from deficiencies in perception or reasoning capabilities. Therefore, we introduce VCR-Bench, a novel benchmark designed to comprehensively evaluate LVLMs' Video Chain-of-Thought Reasoning capabilities. VCR-Bench comprises 859 videos spanning a variety of video content and durations, along with 1,034 high-quality question-answer pairs. Each pair is manually annotated with a stepwise CoT rationale, where every step is tagged to indicate its association with the perception or reasoning capabilities. Furthermore, we design seven distinct task dimensions and propose the CoT score to assess the entire CoT process based on the stepwise tagged CoT rationals. Extensive experiments on VCR-Bench highlight substantial limitations in current LVLMs. Even the top-performing model, o1, only achieves a 62.8% CoT score and an 56.7% accuracy, while most models score below 40%. Experiments show most models score lower on perception than reasoning steps, revealing LVLMs' key bottleneck in temporal-spatial information processing for complex video reasoning. A robust positive correlation between the CoT score and accuracy confirms the validity of our evaluation framework and underscores the critical role of CoT reasoning in solving complex video reasoning tasks. We hope VCR-Bench to serve as a standardized evaluation framework and expose the actual drawbacks in complex video reasoning task.

Despite their impressive performance on complex tasks, current language models (LMs) typically operate in a vacuum: Each input query is processed separately, without retaining insights from previous attempts. Here, we present Dynamic Cheatsheet (DC), a lightweight framework that endows a black-box LM with a persistent, evolving memory. Rather than repeatedly re-discovering or re-committing the same solutions and mistakes, DC enables models to store and reuse accumulated strategies, code snippets, and general problem-solving insights at inference time. This test-time learning enhances performance substantially across a range of tasks without needing explicit ground-truth labels or human feedback. Leveraging DC, Claude 3.5 Sonnet's accuracy more than doubled on AIME math exams once it began retaining algebraic insights across questions. Similarly, GPT-4o's success rate on Game of 24 increased from 10% to 99% after the model discovered and reused a Python-based solution. In tasks prone to arithmetic mistakes, such as balancing equations, DC enabled GPT-4o and Claude to reach near-perfect accuracy by recalling previously validated code, whereas their baselines stagnated around 50%. Beyond arithmetic challenges, DC yields notable accuracy gains on knowledge-demanding tasks. Claude achieved a 9% improvement in GPQA-Diamond and an 8% boost on MMLU-Pro problems. Crucially, DC's memory is self-curated, focusing on concise, transferable snippets rather than entire transcript. Unlike finetuning or static retrieval methods, DC adapts LMs' problem-solving skills on the fly, without modifying their underlying parameters. Overall, our findings present DC as a promising approach for augmenting LMs with persistent memory, bridging the divide between isolated inference events and the cumulative, experience-driven learning characteristic of human cognition.

-- Cartoon avatars have been widely used in various applications, including social media, online tutoring, and gaming. However, existing cartoon avatar datasets and generation methods struggle to present highly expressive avatars with fine-grained facial expressions and are often inspired from real-world identities, raising privacy concerns. T o address these challenges, we propose a novel framework, GenEA va, for generating high-quality cartoon avatars with fine-grained facial expressions. Our approach fine-tunes a state-of-the-art text-to-image diffusion model to synthesize highly detailed and expressive facial expressions. We then incorporate a stylization model that transforms these realistic faces into cartoon avatars while preserving both identity and expression. Leveraging this framework, we introduce the first expressive cartoon avatar dataset, GenEA va 1.0, specifically designed to capture 135 fine-grained facial expressions, featuring 13,230 expressive cartoon avatars with a balanced distribution across genders, racial groups, and age ranges. We demonstrate that our fine-tuned model generates more expressive faces than the state-of-the-art text-to-image diffusion model SDXL. We also verify that the cartoon avatars generated by our framework do not include memorized identities from fine-tuning data. The proposed framework and dataset provide a diverse and expressive benchmark for future research in cartoon avatar generation. I. INTRODUCTION Cartoon avatars have become increasingly important in various digital domains, serving as personalized digital representations in applications such as social media [41], chatbots [22], online tutoring [18], [57], video conferencing [45], virtual reality [5], and video games [40]. As digital communication evolves, cartoon avatars offer a compelling alternative to realistic human representations, providing users with enhanced personalization and privacy, and enriching user engagement and interaction across various platforms.

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often suffer from degraded response quality and heightened susceptibility to hallucinations. To address this trade-off, collaborative decoding, in which a large model assists in generating critical tokens, has emerged as a promising solution. This paradigm leverages the strengths of both model types by enabling high-quality inference through selective intervention of the large model, while maintaining the speed and efficiency of the smaller model. In this work, we present a novel collaborative decoding inference system that allows small models to perform on-device inference while selectively consulting a cloud-based large model for critical token generation. Remarkably, the system achieves a 60% performance gain on CommonsenseQA using only a 0.5B model on an M1 MacBook, with under 7% of tokens generation uploaded to the large model in the cloud.

Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology that integrates a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios. We demonstrate the effectiveness of our approach using Thai as an illustrative case, where intricate phonetic rules and sparse resources are effectively addressed. Our method enables zero-shot voice cloning and improved performance across diverse client applications, ranging from finance to healthcare, education, and law. Extensive evaluations - both subjective and objective - confirm that our model meets state-of-the-art standards, offering a scalable solution for TTS production in data-limited settings, with significant implications for broader industry adoption and multilingual accessibility.

Recently, a growing number of experts in artificial intelligence (AI) and medicine have be-gun to suggest that the use of AI systems, particularly machine learning (ML) systems, is likely to humanise the practice of medicine by substantially improving the quality of clinician-patient relationships. In this thesis, however, I argue that medical ML systems are more likely to negatively impact these relationships than to improve them. In particular, I argue that the use of medical ML systems is likely to comprise the quality of trust, care, empathy, understanding, and communication between clinicians and patients.