Shadow Cone
"Cone," in various scientific contexts, refers to a geometric structure used to model hierarchical relationships, illumination conditions, or data distributions. Current research focuses on developing efficient algorithms and model architectures, such as neural networks and multiplicative weight updates, to leverage cone structures for tasks ranging from multi-modal knowledge graph querying and image synthesis to long video temporal grounding and optimization problems in computer vision and machine learning. These advancements improve the accuracy and efficiency of various applications, including spacecraft navigation, educational tool development, and image analysis.
Papers
Cones 2: Customizable Image Synthesis with Multiple Subjects
Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao
ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models
Huahui Yi, Ziyuan Qin, Wei Xu, Miaotian Guo, Kun Wang, Shaoting Zhang, Kang Li, Qicheng Lao