https://pypi.org/project/embedding-condensation/ Recent updates to the Python Package Index for embedding-condensation en https://pypi.org/project/embedding-condensation/2.0/ Measure layer-wise token embedding cosine similarity, assessing the severity of embedding condensation. Concept from [ICML 2026] Dispersion loss counteracts embedding condensation and improves generalization in small language models. Sun, 17 May 2026 21:35:46 GMT https://pypi.org/project/embedding-condensation/1.1/ Measure layer-wise token embedding cosine similarity, assessing the severity of embedding condensation. Concept from [ICML 2026] Dispersion loss counteracts embedding condensation and improves generalization in small language models. Sun, 17 May 2026 21:34:24 GMT https://pypi.org/project/embedding-condensation/1.0.0/ Measure layer-wise token embedding cosine similarity, assessing the severity of embedding condensation. Concept from [ICML 2026] Dispersion loss counteracts embedding condensation and improves generalization in small language models. Sun, 17 May 2026 21:29:11 GMT https://pypi.org/project/embedding-condensation/0.1.0/ Measure layer-wise token embedding cosine similarity (embedding condensation diagnostic). Sun, 17 May 2026 21:16:37 GMT