论文题目:Multimodal Commonsense Knowledge Distillation for Visual Question Answering (Student Abstract) 发表期刊:2025 AAAI Conference on Artificial Intelligen
1. Reinforcement Learning from Human Feedback Reinforcement Learning from Human Feedback(RLHF)是一种结合了强化学习(Reinforcement Learning, RL)和人类反馈的机器学习方法。这种方法特
论文题目:Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models 发表期刊:2025 The IEEE / CVF Computer Vision and Pattern Recog
论文题目:Grounded Chain-of-Thought for Multimodal Large Language Models 发表期刊:2025 The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search 1.介绍 尽管在自然语言领域取得了显著进展,但语言模型在形式化定理证明方面
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 1.介绍 两个关键内容: 利用公开可用网络数据的数据选择管道,大规模数学预训练 创建了DeepSeekMath语料库:从Common
论文题目:DEST-GNN: A double-explored spatio-temporal graph neural network for multi-site intra-hour PV power forecasting 发表时间:2025 Applied Energy (影响因子:10
论文题目:Graph Spatio-Temporal Networks for Condition Monitoring of Wind Turbine 发表时间:2024 IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, (影响因子:8.7) 论文作者:Xiaoha
论文题目:Cost-effective fault diagnosis of nearby photovoltaic systems using graph neural networks 发表时间:2023 Energy (影响因子:9) 论文作者:Jonas Van Gompel, Domeni
论文题目:Retentive Network: A Successor to Transformer for Large Language Models 发表时间:2023 IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (影响因子:8.9)