Large Language Models (LLMs) have become essential tools across various domains due to their impressive capabilities in understanding and generating human-like text. The ability to accurately answer multiple-choice questions (MCQs) holds significant value in education, particularly in automated tutoring systems and assessment platforms. However, adapting LLMs to handle MCQ tasks effectively remains challenging due to the hallucinations and unclear prompts. This work explores the potential of Microsoft's PHI-3\cite{Abdin2024}, a compact yet efficient LLM, for MCQ answering. Our contributions include fine-tuning the model on the TruthfulQA dataset, designing optimized prompts to enhance model performance, and evaluating using perplexity and traditional metrics like accuracy and F1 score. Results show a remarkable improvement in PHI-3.5's MCQ handling post-fine-tuning, with perplexity decreasing from 4.68 to 2.27, and accuracy rising from 62\% to 90.8\%. This research underlines the importance of efficient models in adaptive learning systems and educational assessments, paving the way for broader integration into the classroom, particularly in fields like test preparation, student feedback, and personalized learning.

Motivated by deep learning regimes with multiple interacting yet distinct model components, we introduce learning diagrams, graphical depictions of training setups that capture parameterized learning as data rather than code. A learning diagram compiles to a unique loss function on which component models are trained. The result of training on this loss is a collection of models whose predictions ``agree" with one another. We show that a number of popular learning setups such as few-shot multi-task learning, knowledge distillation, and multi-modal learning can be depicted as learning diagrams. We further implement learning diagrams in a library that allows users to build diagrams of PyTorch and Flux.jl models. By implementing some classic machine learning use cases, we demonstrate how learning diagrams allow practitioners to build complicated models as compositions of smaller components, identify relationships between workflows, and manipulate models during or after training. Leveraging a category theoretic framework, we introduce a rigorous semantics for learning diagrams that puts such operations on a firm mathematical foundation.

Large language models (LLMs) have demonstrated their remarkable capacity across a variety of tasks. However, reasoning remains a challenge for LLMs. To improve LLMs' reasoning ability, process supervision has proven to be better than outcome supervision. In this work, we study using Monte Carlo Tree Search (MCTS) to generate process supervision data with LLMs themselves for training them. We sample reasoning steps with an LLM and assign each step a score that captures its "relative correctness," and the LLM is then trained by minimizing weighted log-likelihood of generating the reasoning steps. This generate-then-train process is repeated iteratively until convergence.Our experimental results demonstrate that the proposed methods considerably improve the performance of LLMs on two mathematical reasoning datasets. Furthermore, models trained on one dataset also exhibit improved performance on the other, showing the transferability of the enhanced reasoning ability.

In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been significantly improved during both the pre-training and post-training stages. In terms of pre-training, we have scaled the high-quality pre-training datasets from the previous 7 trillion tokens to 18 trillion tokens. This provides a strong foundation for common sense, expert knowledge, and reasoning capabilities. In terms of post-training, we implement intricate supervised finetuning with over 1 million samples, as well as multistage reinforcement learning. Post-training techniques enhance human preference, and notably improve long text generation, structural data analysis, and instruction following. To handle diverse and varied use cases effectively, we present Qwen2.5 LLM series in rich sizes. Open-weight offerings include base and instruction-tuned models, with quantized versions available. In addition, for hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2.5-Turbo and Qwen2.5-Plus, both available from Alibaba Cloud Model Studio. Qwen2.5 has demonstrated top-tier performance on a wide range of benchmarks evaluating language understanding, reasoning, mathematics, coding, human preference alignment, etc. Specifically, the open-weight flagship Qwen2.5-72B-Instruct outperforms a number of open and proprietary models and demonstrates competitive performance to the state-of-the-art open-weight model, Llama-3-405B-Instruct, which is around 5 times larger. Qwen2.5-Turbo and Qwen2.5-Plus offer superior cost-effectiveness while performing competitively against GPT-4o-mini and GPT-4o respectively. Additionally, as the foundation, Qwen2.5 models have been instrumental in training specialized models such as Qwen2.5-Math, Qwen2.5-Coder, QwQ, and multimodal models.

Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud operations are job scheduling and resource management, which are critical for optimizing system performance and ensuring timely and cost-effective service delivery. However, the dynamic and heterogeneous nature of cloud environments presents significant challenges for these tasks, as workloads and resource availability can fluctuate unpredictably. Traditional approaches, including heuristic and meta-heuristic algorithms, often struggle to adapt to these real-time changes due to their reliance on static models or predefined rules. Deep Reinforcement Learning (DRL) has emerged as a promising solution to these challenges by enabling systems to learn and adapt policies based on continuous observations of the environment, facilitating intelligent and responsive decision-making. This survey provides a comprehensive review of DRL-based algorithms for job scheduling and resource management in cloud computing, analyzing their methodologies, performance metrics, and practical applications. We also highlight emerging trends and future research directions, offering valuable insights into leveraging DRL to advance both job scheduling and resource management in cloud computing.

We introduce Interactionalism as a new set of guiding principles and heuristics for the design and architecture of learning now available due to Generative AI (GenAI) platrforms. Specifically, we articulate interactional intelligence as a net new skill set that is increasingly important when core cognitive tasks are automatable and augmentable by GenAI functions. We break down these skills into core sets of meta-cognitive and meta-emotional components and show how working with Large Language Model (LLM)-based agents can be proactively used to help develop learners. Interactionalism is not advanced as a theory of learning; but as a blueprint for the practice of learning - in coordination with GenAI. This approach is focused on explicit pedagogical moves, gestures and maneuvers that focus on the dialogical and dynamics of learning together with GenAI agents. The value of this approach is in anticipation of growing reliance on, and integration with, AI as a co-agent with humans, and an important factor in the production function of'skills' and'knowledge' across many domains.

Although sign language recognition aids non-hearing-impaired understanding, many hearing-impaired individuals still rely on sign language alone due to limited literacy, underscoring the need for advanced sign language production and translation (SLP and SLT) systems. In the field of sign language production, the lack of adequate models and datasets restricts practical applications. Existing models face challenges in production accuracy and pose control, making it difficult to provide fluent sign language expressions across diverse scenarios. Additionally, data resources are scarce, particularly high-quality datasets with complete sign vocabulary and pose annotations. To address these issues, we introduce CNText2Sign and CNSign, comprehensive datasets to benchmark SLP and SLT, respectively, with CNText2Sign covering gloss and landmark mappings for SLP, and CNSign providing extensive video-to-text data for SLT. To improve the accuracy and applicability of sign language systems, we propose the AuraLLM and SignMST-C models. AuraLLM, incorporating LoRA and RAG techniques, achieves a BLEU-4 score of 50.41 on the CNText2Sign dataset, enabling precise control over gesture semantics and motion. SignMST-C employs self-supervised rapid motion video pretraining, achieving a BLEU-4 score of 31.03/32.08 on the PHOENIX2014-T benchmark, setting a new state-of-the-art. These models establish robust baselines for the datasets released for their respective tasks.

This work introduces a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios: Mixture of Tasks and Noisy Demonstrations. We systematically evaluate the effectiveness of Influence Functions (IFs) as a selection tool for these settings, highlighting the potential for IFs to better capture the informativeness of examples within the demonstration pool. For the Mixture of Tasks setting, demonstrations are drawn from 28 diverse tasks, including MMLU, BigBench, StrategyQA, and CommonsenseQA. We demonstrate that combining BertScore-Recall (BSR) with an IF surrogate model can significantly improve performance, leading to average absolute accuracy gains of 0.37\% and 1.45\% for 3-shot and 5-shot setups when compared to traditional ICL metrics. In the Noisy Demonstrations setting, we examine scenarios where demonstrations might be mislabeled. Our experiments show that reweighting traditional ICL selectors (BSR and Cosine Similarity) with IF-based selectors boosts accuracy by an average of 2.90\% for Cosine Similarity and 2.94\% for BSR on noisy GLUE benchmarks. In sum, we propose a robust framework for demonstration selection that generalizes beyond traditional ICL, offering valuable insights into the role of IFs for Indirect ICL.

Reasoning is fundamental to human intelligence, and critical for problem-solving, decision-making, and critical thinking. Reasoning refers to drawing new conclusions based on existing knowledge, which can support various applications like clinical diagnosis, basic education, and financial analysis. Though a good number of surveys have been proposed for reviewing reasoning-related methods, none of them has systematically investigated these methods from the viewpoint of their dependent knowledge base. Both the scenarios to which the knowledge bases are applied and their storage formats are significantly different. Hence, investigating reasoning methods from the knowledge base perspective helps us better understand the challenges and future directions. To fill this gap, this paper first classifies the knowledge base into symbolic and parametric ones. The former explicitly stores information in human-readable symbols, and the latter implicitly encodes knowledge within parameters. Then, we provide a comprehensive overview of reasoning methods using symbolic knowledge bases, parametric knowledge bases, and both of them. Finally, we identify the future direction toward enhancing reasoning capabilities to bridge the gap between human and machine intelligence.

Missing attribute issues are prevalent in the graph learning, leading to biased outcomes in Graph Neural Networks (GNNs). Existing methods that rely on feature propagation are prone to cold start problem, particularly when dealing with attribute resetting and low-degree nodes, which hinder effective propagation and convergence. To address these challenges, we propose AttriReBoost (ARB), a novel method that incorporates propagation-based method to mitigate cold start problems in attribute-missing graphs. ARB enhances global feature propagation by redefining initial boundary conditions and strategically integrating virtual edges, thereby improving node connectivity and ensuring more stable and efficient convergence. This method facilitates gradient-free attribute reconstruction with lower computational overhead. The proposed method is theoretically grounded, with its convergence rigorously established. Extensive experiments on several real-world benchmark datasets demonstrate the effectiveness of ARB, achieving an average accuracy improvement of 5.11% over state-of-the-art methods. Additionally, ARB exhibits remarkable computational efficiency, processing a large-scale graph with 2.49 million nodes in just 16 seconds on a single GPU. Our code is available at https://github.com/limengran98/ARB.