{"ID":2823480,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00366","arxiv_id":"2601.00366","title":"BERT-JEPA: Reorganizing CLS Embeddings for Language-Invariant Semantics","abstract":"Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to BERT-style models, working to combat a collapsed [CLS] embedding space and turning it into a language-agnostic space. This new structure leads to increased performance across multilingual benchmarks.","short_abstract":"Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to BERT-style models, working to combat a collapsed [CLS] embedding space and turning it in...","url_abs":"https://arxiv.org/abs/2601.00366","url_pdf":"https://arxiv.org/pdf/2601.00366v1","authors":"[\"Taj Gillin\",\"Adam Lalani\",\"Kenneth Zhang\",\"Marcel Mateos Salles\"]","published":"2026-01-01T14:59:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}