Embeddings are one of the fundamental building blocks for data analysis tasks. Embeddings are already essential tools for large language models and image analysis, and their use is being extended to many other research domains. The generation of these distributed representations is often a data- and computation-expensive process; yet the holistic analysis and adjustment of them after they have been created is still a developing area. In this paper, we first propose a very general quantitatively measure for the presence of features in the embedding data based on if it can be learned. We then devise a method to remove or alleviate undesired features in the embedding while retaining the essential structure of the data. We use a Domain Adversarial Network (DAN) to generate a non-affine transformation, but we add constraints to ensure the essential structure of the embedding is preserved. Our empirical results demonstrate that the proposed algorithm significantly outperforms the state-of-art unsupervised algorithm on several data sets, including novel applications from the industry.
Exploiting Differential Flatness for Efficient Learning-based Model Predictive Control of Constrained Multi-Input Control Affine Systems
Learning Systems and Robotics Lab at the Technical University of Munich(慕尼黑技术大学学习系统与机器人实验室);Learning Systems and Robotics Lab at the University of Toronto Institute for Aerospace Studies (UTIAS) and the Vector Institute for Artificial Intelligence(多伦多航空航天研究所(UTIAS)和向量人工智能研究所的学习系统与机器人实验室)
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(北京未来区块链与隐私计算先进创新中心);Beihang University(北京航空航天大学);Hangzhou International Innovation Institute(杭州国际创新研究院);Xreal;Renmin University(中国人民大学);Peking University(北京大学);Beijing Academy of Blockchain and Edge Computing (BABEC)(北京区块链与边缘计算研究院)