Recent advances such as OpenAI-o1 and DeepSeek R1 have demonstrated the potential of Reinforcement Learning (RL) to enhance reasoning abilities in Large Language Models (LLMs). While open-source replication efforts have primarily focused on mathematical and coding domains, methods and resources for developing general reasoning capabilities remain underexplored. This gap is partly due to the challenge of collecting diverse and verifiable reasoning data suitable for RL. We hypothesize that logical reasoning is critical for developing general reasoning capabilities, as logic forms a fundamental building block of reasoning. In this work, we present SynLogic, a data synthesis framework and dataset that generates diverse logical reasoning data at scale, encompassing 35 diverse logical reasoning tasks. The SynLogic approach enables controlled synthesis of data with adjustable difficulty and quantity. Importantly, all examples can be verified by simple rules, making them ideally suited for RL with verifiable rewards. In our experiments, we validate the effectiveness of RL training on the SynLogic dataset based on 7B and 32B models. SynLogic leads to state-of-the-art logical reasoning performance among open-source datasets, surpassing DeepSeek-R1-Distill-Qwen-32B by 6 points on BBEH. Furthermore, mixing SynLogic data with mathematical and coding tasks improves the training efficiency of these domains and significantly enhances reasoning generalization. Notably, our mixed training model outperforms DeepSeek-R1-Zero-Qwen-32B across multiple benchmarks. These findings position SynLogic as a valuable resource for advancing the broader reasoning capabilities of LLMs. We will open-source both the data synthesis pipeline and the SynLogic dataset.

Sound event detection identifies specific auditory signal occurrences to recognize the sound event class and its temporal localization. While the Convolutional Recurrent Neural Network with a mean-teacher framework shows impressive SED performance, its effectiveness is hindered by its small receptive field, leading to inadequate consideration of global temporal information and imprecise event boundary localization. Moreover, existing detectors overlook the intricate interplay between temporal and frequency information, compromising detection accuracy. Simultaneously, there is an oversight in interactions between student and teacher models, leading to the teacher conveying inaccurate knowledge to the student. To solve these challenges, this paper proposes a novel robust detector named HTA-CTD, incorporating the Hierarchical Temporal Attention (HTA) and Competent Teacher Network (CTN). HTA introduces an adaptive temporal-frequency feature extraction method, while CTN minimizes reliance on strong labels. Experiments on challenging benchmarks show that our HTA-CTD outperforms the state-of-the-art detector and achieves leading performance.

The amount and quality of mathematical language in the family are positively associated with promoting children’s mathematical abilities. However, mathematical language in many families is poor. Through need-finding investigation, we developed MathKingdom, a voice-agent-based game that helps children aged 4–7 learn and use rich, accurate mathematical language (e.g., mathematical expressions related to measurement, sequence, patterns). The game has four flows, in which users can wake up, transform, decorate, and perform as their avatars, as well as practice basic mathematical vocabulary, mathematical single sentences, coherent mathematical statements, and free expression. We refined the system design through wizard-of-oz testing and then evaluated it with 18 families. The results showed that MathKingdom effectively engaged children, enhanced their mathematical language skills and mathematical abilities, and encouraged parent-child conversations about math.