研究人员开发了SolarTformer，一个使用Transformer架构和自注意力机制的深度学习模型，用于更准确的短期太阳能发电预测。该模型整合了气象数据和电站特定的元数据，以捕捉时间依赖性和空间变异性，表现优于以往的方法。另外，一项新研究利用多模态融合和基于Transformer的架构，探索了通过社交媒体内容预测诱发愉悦感，准确率达到0.6624。另一篇论文比较了n-gram模型与LSTM和Transformer等神经网络在事件日志预测中的表现，发现n-gram在资源消耗显著减少的情况下提供了可比的准确性。最后，一篇论文介绍了LoRA适配的Transformer中的子令牌路由，通过压缩令牌内的信息来提高效率，从而增强了语言建模和下游任务的性能。 AI
影响 引入了用于太阳能预测、情感预测、事件日志分析和高效模型适配的新型基于Transformer的方法。
排序理由 该集群包含多篇详细介绍新模型和方法的学术论文，包括SolarTformer和LoRA中的子令牌路由。
AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →
arXiv:2510.09382v2 Announce Type: replace Abstract: Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for emotion recognition often rely on heuristic, data-driven, or model-based definit…
arXiv:2604.24306v1 Announce Type: new Abstract: Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based deep learning model, inspired by transformer architecture, is used for short-term…
arXiv:2604.23753v1 Announce Type: cross Abstract: Multimodal affective computing analyzes user-generated social media content to predict emotional states. However, a critical gap remains in understanding how visual content shapes cognitive interpretations and elicits specific aff…
Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based deep learning model, inspired by transformer architecture, is used for short-term solar power forecasting. Our proposed model, "S…
Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based deep learning model, inspired by transformer architecture, is used for short-term solar power forecasting. Our proposed model, "S…
We compare lightweight automata-based models (n-grams) with neural architectures (LSTM, Transformer) for next-activity prediction in streaming event logs. Experiments on synthetic patterns and five real-world process mining datasets show that n-grams with appropriate context wind…
We compare lightweight automata-based models (n-grams) with neural architectures (LSTM, Transformer) for next-activity prediction in streaming event logs. Experiments on synthetic patterns and five real-world process mining datasets show that n-grams with appropriate context wind…
Sub-token routing offers a finer control axis for transformer efficiency than the coarse units used in most prior work, such as tokens, pages, heads, or layers. In this paper, we study routing within a token representation itself in LoRA-adapted transformers. The motivation is th…
Sub-token routing offers a finer control axis for transformer efficiency than the coarse units used in most prior work, such as tokens, pages, heads, or layers. In this paper, we study routing within a token representation itself in LoRA-adapted transformers. The motivation is th…