| license: mit | |
| pipeline_tag: text-generation | |
| # Self-Conditioned Flow Map Language Models via Fixed-Point Flows | |
| This repository contains checkpoints for **ELF**, **ELF\***, and **FMLM\*** introduced in the paper [Self-conditioned Flow Map Language Models via Fixed-point Flows](https://huggingface.co/papers/2607.00714). | |
| All models use the **ELF-B** backbone (12 layers, hidden 768, 12 heads, ~105M parameters). | |
| ## Released Models | |
| - **ELF**: Self-conditioned flow teacher. | |
| - **ELF\***: Self-conditioning-free fixed-point denoiser (CDEQ). | |
| - **FMLM\***: Few-step flow map (two-time denoiser). | |
| ## Code and Usage | |
| The official codebase for training, evaluation, and sampling instructions can be found on GitHub: | |
| 👉 [self-conditioned-fmlm GitHub Repository](https://github.com/Ugness/self-conditioned-fmlm) | |
| ### Citation | |
| If you find this work useful, please consider citing: | |
| ```bibtex | |
| @article{yoo2026selfconditioned, | |
| title={Self-Conditioned Flow Map Language Models via Fixed-Point Flows}, | |
| author={Jaehoon Yoo and Wonjung Kim and Floor Eijkelboom and Chanhyuk Lee | |
| and Nicholas M. Boffi and Seunghoon Hong and Jinwoo Kim}, | |
| journal={arXiv preprint arXiv:2607.00714}, | |
| year={2026}, | |
| } | |
| ``` |