Semantic Description
Semantic description focuses on representing and understanding the meaning of data, aiming to bridge the gap between raw data and its inherent meaning for various applications. Current research emphasizes integrating semantic information with other modalities (e.g., geometric, visual, temporal) using techniques like transformer networks, generative models (e.g., diffusion models, NeRFs), and Siamese architectures, often within a parameter-efficient fine-tuning framework. This work is significant for improving the accuracy and efficiency of tasks ranging from robot-human interaction and image processing to natural language understanding and information retrieval, ultimately leading to more robust and interpretable AI systems.
78papers
Papers
April 25, 2025
April 12, 2025
March 25, 2025
March 12, 2025
March 4, 2025
January 19, 2025
January 13, 2025
December 17, 2024
December 15, 2024
December 6, 2024
December 3, 2024
November 19, 2024
November 7, 2024
October 31, 2024