Theory-of-Mind (ToM) is a core human cognitive capacity for attributing mental states to self and others. Wimmer and Perner demonstrated that humans progress from first- to higher-order ToM within a short span, completing this development before formal education or advanced skill acquisition. In contrast, neural networks represented by autoregressive language models progress from first- to higher-order ToM only alongside gains in advanced skills like reasoning, leaving open whether their trajectory can unfold independently, as in humans. In this research, we provided evidence that neural networks could spontaneously generalize from first- to higher-order ToM without relying on advanced skills. We introduced a neural Theory-of-Mind network (ToMNN) that simulated a minimal cognitive system, acquiring only first-order ToM competence. Evaluations of its second- and third-order ToM abilities showed accuracies well above chance. Also, ToMNN exhibited a sharper decline when generalizing from first- to second-order ToM than from second- to higher orders, and its accuracy decreased with greater task complexity. These perceived difficulty patterns were aligned with human cognitive expectations. Furthermore, the universality of results was confirmed across different parameter scales. Our findings illuminate machine ToM generalization patterns and offer a foundation for developing more human-like cognitive systems.

Artificial Intelligence (AI) is increasingly permeating classrooms worldwide, yet its adoption in schools of developing countries remains under-explored. This paper investigates AI adoption, usage patterns, and perceived impact in Pakistani K-12 schools based on a survey of 125 educators. The questionnaire covered educator's familiarity with AI, frequency and modes of use, and attitudes toward AI's benefits and challenges. Results reveal a generally positive disposition towards AI: over two-thirds of teachers expressed willingness to adopt AI tools given proper support and many have begun integrating AI for lesson planning and content creation. However, AI usage is uneven - while about one-third of respondents actively use AI tools frequently, others remain occasional users. Content generation emerged as the most common AI application, whereas AI-driven grading and feedback are rarely used. Teachers reported moderate improvements in student engagement and efficiency due to AI, but also voiced concerns about equitable access. These findings highlight both the enthusiasm for AI's potential in Pakistan's schools and the need for training and infrastructure to ensure inclusive and effective implementation.

Artificial intelligence (AI) is rapidly reshaping educational practice, challenging long held assumptions about teaching and learning. This article integrates conceptual perspectives from recent books (Genesis by Eric Schmidt, Henry Kissinger and Craig Mundie, CoIntelligence by Ethan Mollick, and The Inevitable by Kevin Kelly) with empirical insights from popular AI podcasts and Anthropic public releases. We examine seven key domains: emotional support, creativity, contextual understanding, student engagement, problem solving, ethics and morality, and collaboration. For each domain, we explore AI capabilities, opportunities for transformative change, and emerging best practices, drawing equally from theoretical analysis and real world observations. Overall, we find that AI, when used thoughtfully, can complement and enhance human educators in fostering richer learning experiences across cognitive, social, and emotional dimensions. We emphasize an optimistic yet responsible outlook: educators and students should actively shape AI integration to amplify human potential in creativity, ethical reasoning, collaboration, and beyond, while maintaining a focus on human centric values.

Practical lab education in computer science often faces challenges such as plagiarism, lack of proper lab records, unstructured lab conduction, inadequate execution and assessment, limited practical learning, low student engagement, and absence of progress tracking for both students and faculties, resulting in graduates with insufficient hands-on skills. In this paper, we introduce AsseslyAI, which addresses these challenges through online lab allocation, a unique lab problem for each student, AI-proctored viva evaluations, and gamified simulators to enhance engagement and conceptual mastery. While existing platforms generate questions based on topics, our framework fine-tunes on a 10k+ question-answer dataset built from AI/ML lab questions to dynamically generate diverse, code-rich assessments. Validation metrics show high question-answer similarity, ensuring accurate answers and non-repetitive questions. By unifying dataset-driven question generation, adaptive difficulty, plagiarism resistance, and evaluation in a single pipeline, our framework advances beyond traditional automated grading tools and offers a scalable path to produce genuinely skilled graduates.

Knowledge distillation is a common paradigm for transferring capabilities from larger models to smaller ones. While traditional distillation methods leverage a probabilistic divergence over the output of the teacher and student models, feature-based distillation methods often minimize variants of Euclidean norms between the hidden layer representations. The main goal is for the student to mimic the structure of the feature space of the teacher. In this work, we theoretically show that existing feature distillation methods, such as projection based mean squared loss or Centered Kernel Alignment (CKA), cannot capture the feature structure, even under zero loss. We then motivate the use of Procrustes distance and the Frobenius norm of Feature Gram Matrix, distances already common in the context of measuring representational alignment, as distillation losses. We show that feature distillation through our method showcases statistically significant improvement in distillation performance across language models families (BERT and OPT) in classification and instruction-following tasks by up to 2 percentage points, showcasing the potential of integrating feature geometry into existing distillation methods. While large models are achieving state-of-the-art results across almost all vision and language tasks, the emergent abilities these models exhibit (Wei et al., 2022; Liang et al., 2023b) are often inaccessible to the public as a result of their inherent size and operating costs. Knowledge Distillation (KD) is one of the many paradigms that aim to bridge the gap between size and performance by inducing ways of transferring knowledge and abilities from a larger, complex model (teacher) to a smaller and accessible model (student).

Accurate and timely forecasting of heavy rainfall remains a critical challenge for modern society. Precipitation exhibits a highly imbalanced distribution: most observations record no or light rain, while heavy rainfall events are rare. Such an imbalanced distribution obstructs deep learning models from effectively predicting heavy rainfall events. To address this challenge, we treat rainfall forecasting explicitly as a long-tailed learning problem, identifying the insufficient representation of heavy rainfall events as the primary barrier to forecasting accuracy. Therefore, we introduce DPSformer, a long-tail-aware model that enriches representation of heavy rainfall events through a high-resolution branch. For heavy rainfall events $ \geq $ 50 mm/6 h, DPSformer lifts the Critical Success Index (CSI) of a baseline Numerical Weather Prediction (NWP) model from 0.012 to 0.067. For the top 1% coverage of heavy rainfall events, its Fraction Skill Score (FSS) exceeds 0.45, surpassing existing methods. Our work establishes an effective long-tailed paradigm for heavy rainfall prediction, offering a practical tool to enhance early warning systems and mitigate the societal impacts of extreme weather events.

Recent advances in multimodal time series learning underscore a paradigm shift from analytics centered on basic patterns toward advanced time series understanding and reasoning. However, existing multimodal time series datasets mostly remain at the level of surface alignment and question answering, without reaching the depth of genuine reasoning. The absence of well-defined tasks that genuinely require time series reasoning, along with the scarcity of high-quality data, has limited progress in building practical time series reasoning models (TSRMs). To this end, we introduce Time Series Reasoning Suite (TSR-Suite), which formalizes four atomic tasks that span three fundamental capabilities for reasoning with time series: (1) perception, acquired through scenario understanding and causality discovery; (2) extrapolation, realized via event-aware forecasting; and (3) decision-making, developed through deliberation over perception and extrapolation. TSR-Suite is the first comprehensive time series reasoning suite that supports not only thorough evaluation but also the data pipeline and training of TSRMs. It contains more than 23K samples, of which 2.3K are carefully curated through a human-guided hierarchical annotation process. Building on this foundation, we introduce TimeOmni-1, the first unified reasoning model designed to address diverse real-world problems demanding time series reasoning. The model is trained in multiple stages, integrating a mixture of task scenarios, novel reward functions, and tailored optimizations. Experiments show that TimeOmni-1 delivers strong out-of-distribution generalization across all tasks and achieves a high rate of valid responses. It significantly improves causality discovery accuracy (64.0% vs. 35.9% with GPT-4.1) and raises the valid response rate by over 6% compared to GPT-4.1 on the event-aware forecasting task.

High-quality, multi-modal benchmarks are crucial for advancing scientific reasoning in large models yet their manual creation is costly and unscalable. To address this bottleneck, we explore the potential for transforming Text-Only QA Pairs (TQAs) into high-quality Multi-Modal QA Pairs (MMQAs), which include three parts: 1) Task Definition \& Evaluation Rubric: We develop a TQA-to-MMQA framework and establish a comprehensive, multi-dimensional MMQA quality rubric that provides principles for the transformation. 2) Benchmark Construction: Then we construct two extensive benchmarks to rigorously evaluate state-of-the-art generation \& understanding models on the distinct tasks of MMQA generation \& MMQA quality evaluation. 3) Preliminary Solution: We develop an agentic system (Q-Mirror), which operationalizes our framework by integrating MMQA generation and evaluation into a closed loop for iterative refinement. Our experiments show that while state-of-the-art models can generate MMQAs, their outputs still leave substantial gaps, underscoring the need for reliable evaluation. We further demonstrate that top-tier understanding models align closely with human judgment in MMQA quality assessment. Leveraging both insights, the Q-Mirror agent raises average scores from 78.90 to 85.22 and pass rates from 72\% to 95\%, offering a practical path to large-scale scientific benchmarks.

Large language models (LLMs) are increasingly positioned as solutions for education, yet evaluations often reduce their impact to narrow performance metrics. This paper reframes the question by asking "what kind of impact should LLMs have in education?" Drawing on Biesta's tripartite account of good education: qualification, socialisation, and subjectification, we present a meta-analysis of 133 experimental and quasi-experimental studies (k = 188). Overall, the impact of LLMs on student learning is positive but uneven. Strong effects emerge in qualification, particularly when LLMs function as tutors in sustained interventions. Socialisation outcomes appear more variable, concentrated in sustained, reflective interventions. Subjectification, linked to autonomy and learner development, remains fragile, with improvements confined to small-scale, long-term studies. This purpose-level view highlights design as the decisive factor: without scaffolds for participation and agency, LLMs privilege what is easiest to measure while neglecting broader aims of education. For HCI and education, the issue is not just whether LLMs work, but what futures they enable or foreclose.

Geometric Problem Solving (GPS) poses a unique challenge for Multimodal Large Language Models (MLLMs), requiring not only the joint interpretation of text and diagrams but also iterative visuospatial reasoning. While existing approaches process diagrams as static images, they lack the capacity for dynamic manipulation--a core aspect of human geometric reasoning involving auxiliary line construction and affine transformations. GeoSketch integrates: (1) a Perception module that abstracts diagrams into structured logic forms, (2) a Symbolic Reasoning module that applies geometric theorems to decide the next deductive step, and (3) a Sketch Action module that executes operations such as drawing auxiliary lines or applying transformations, thereby updating the diagram in a closed loop. To train this agent, we develop a two-stage pipeline: supervised fine-tuning on 2,000 symbolic-curated trajectories followed by reinforcement learning with dense, symbolic rewards to enhance robustness and strategic exploration. To evaluate this paradigm, we introduce the GeoSketch Benchmark, a high-quality set of 390 geometry problems requiring auxiliary construction or affine transformations. Experiments on strong MLLM baselines demonstrate that GeoSketch significantly improves stepwise reasoning accuracy and problem-solving success over static perception methods. Work done during an internship at Hainan University. With the advent of Multimodal Large Language Models (MLLMs) (OpenAI, 2024; Comanici et al., 2025; Hong et al., 2025), Geometric Problem Solving (GPS) presents a unique challenge to MLLMs, demanding not only the joint understanding of text and diagrams but also rigorous, multi-step deductive reasoning (Zhang et al., 2023; Qiao et al., 2024; He et al., 2025). While modern MLLMs can ingest multimodal inputs, their reasoning output remains confined to static text. This limits the use of dynamic and visuospatial strategies in geometric problem solving, which becomes particularly evident in complex tasks requiring multi-stage manipulation.