---

1. Co-LMLM: Continuous-Query Limited Memory Language Models
   2026-07-08alphaXiv arXiv S2
2. The State-Prediction Separation Hypothesis
   2026-07-01alphaXiv arXiv S2
3. Lost in Backpropagation: The LM Head is a Gradient Bottleneck
   arXiv.org2026-03-10alphaXiv arXiv S2
4. Gaperon: A Peppered English-French Generative Language Model Suite
   Annual Meeting of the Association for Computational Linguistics2026S2
5. Biomed-Enriched: Data-Efficient Biomedical Pretraining via Paragraph-Level Annotation
   Annual Meeting of the Association for Computational Linguistics2026S2
6. Gaperon: A Peppered English-French Generative Language Model Suite
   arXiv.org2025-10-29alphaXiv arXiv S2
7. Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content
   arXiv.org2025-06-25alphaXiv arXiv S2
8. Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
   2025-03-04alphaXiv arXiv S2
9. Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
   arXiv.org2025S2
10. Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck
    arXiv.org2024-04-11alphaXiv arXiv S2
11. On the Scaling Laws of Geographical Representation in Language Models
    International Conference on Language Resources and Evaluation2024-02-29alphaXiv arXiv S2
12. Anisotropy Is Inherent to Self-Attention in Transformers
    Conference of the European Chapter of the Association for Computational Linguistics2024-01-22alphaXiv arXiv S2
13. Headless Language Models: Learning without Predicting with Contrastive Weight Tying
    International Conference on Learning Representations2023-09-15alphaXiv arXiv S2
14. Is Anisotropy Inherent to Transformers?
    arXiv.org2023-06-13alphaXiv arXiv S2
15. MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling
    arXiv.org2022-12-14alphaXiv arXiv S2