2 papers
cs.CL2025
Gemini Embedding: Generalizable Embeddings from Gemini
Jinhyuk Lee, Feiyang Chen, Sahil Dua +44
In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini…
cs.LG2025
Towards a Learning Theory of Representation Alignment
Francesco Insulla, Shuo Huang, Lorenzo Rosasco
It has recently been argued that AI models' representations are becoming aligned as their scale and performance increase. Empirical analyses have been designed to support this idea…