VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
为解决SVG生成、编辑等缺乏专业级基准问题,提出VectorGym,采用多任务强化学习方法优化,并提供人类标注数据和评估指标。
为解决SVG生成、编辑等缺乏专业级基准问题,提出VectorGym,采用多任务强化学习方法优化,并提供人类标注数据和评估指标。
This work addresses the challenge of score estimation in the presence of latent variables, where conventional denoising score matching (DSM) suffers from high variance at low noise levels, and target score matching (TSM) is inapplicable due to the unavailability of clean-data scores. To overcome this limitation, the authors propose Latent-variable Target Score Matching (LTSM), which extends TSM to settings with latent variables for the first time. LTSM leverages the score of the joint distribution to provide low-variance supervision for the marginal score and integrates DSM into a hybrid training strategy that ensures robustness across varying noise scales. Experimental results demonstrate that LTSM substantially reduces estimation variance, leading to improved score estimation accuracy and enhanced generative sample quality.
To address the scarcity of bioacoustic data, high annotation costs, and insufficient cross-taxa coverage, this study introduces iNatSound—the first large-scale, multi-taxon (birds, mammals, insects, etc.), weakly supervised global bioacoustic dataset, comprising 230,000 audio recordings from over 5,500 species, sourced from iNaturalist citizen science observations. Innovatively integrating field-collected weakly labeled audio, iNatSound supports both single-species classification and multi-label learning. A rigorous cross-dataset evaluation protocol is designed to validate its utility as a pretraining resource for downstream strongly labeled tasks. Leveraging contrastive learning with multiple backbone architectures (e.g., ResNet, EfficientNet), models pretrained on iNatSound achieve significant performance gains across multiple acoustic recognition benchmarks. The dataset is publicly released, establishing a foundational resource for ecological AI and participatory biodiversity monitoring.
This work addresses the challenge in self-supervised learning that high-dimensional representations are difficult to explicitly maximize in terms of mutual information, and existing methods often fail to fully achieve maximum entropy. To this end, the authors propose a radial Gaussianization loss that aligns the feature norms with a chi-squared distribution, thereby expanding the class of feature distributions amenable to transformation into a standard normal distribution. This approach effectively attenuates higher-order dependencies and enhances representation diversity. Integrated into the VCReg framework, the method optimizes the statistical properties of features to more comprehensively approximate a high-dimensional Gaussian distribution. Experiments demonstrate significant improvements in both the informativeness and discriminability of learned representations on both synthetic and real-world datasets.
This work addresses critical limitations in existing personalized dietary guidance approaches—namely, their frequent neglect of real-world constraints, insufficient interpretability, and lack of a unified evaluation benchmark. To bridge this gap, the authors introduce the first graph–language integrated benchmark for nutritional health, which synthesizes multimodal real-world data including health records, food composition, and accessibility. They construct a knowledge graph linking demographics, medical conditions, dietary behaviors, and resource constraints, and propose a unified evaluation framework centered on three core tasks: risk identification, personalized recommendation, and natural language question answering. Leveraging a hybrid architecture combining graph neural networks and large language models, the approach enables resource-aware, interpretable nutritional interventions. Experiments not only uncover dietary patterns significantly associated with health risks but also yield actionable insights for practical deployment and establish a robust baseline for future research.
研究构建了CareMirror系统,通过照护者和临床医生界面连接,解决痴呆症照护者福祉问题,采用半结构化访谈探讨其期望与担忧。
本文探讨了社会网络中不平等度量的隔离单调性标准,通过特定网络结构变换来评估不平等度量方法的有效性。
研究解决了量子网络中路径选择和配置问题,通过构建分层图来计算最短路径,以平衡纠缠的速率和保真度,并针对不同效用函数提供了近似最优解。
研究针对IoT应用被厂商放弃后存在的安全风险,通过分析61,500个Android应用的安全隐患,发现73.6%的应用存在安全问题。
本文针对LLM真实性基准测试中的表面特征泄露问题,提出了一种名为Audit-Prune的方法来清理这些数据集,从而减少模型利用非预期线索的机会。