ELF-L-owt / README.md
nielsr's picture
nielsr HF Staff
Add model card and metadata
0f4f60a verified
|
raw
history blame
1.82 kB
metadata
license: mit
pipeline_tag: text-generation

ELF: Embedded Language Flows

ELF is a class of continuous diffusion language models based on continuous-time Flow Matching. Unlike existing diffusion language models (DLMs), ELF predominantly stays within the continuous embedding space until the final time step, where it maps to discrete tokens using a shared-weight network. This formulation makes it straightforward to adapt established techniques from image-domain diffusion models, such as classifier-free guidance (CFG).

Evaluation and Inference

The official implementation is provided in JAX. To evaluate the pre-trained checkpoints, follow the installation instructions in the GitHub repository and use the following commands from the src/ directory:

Unconditional Generation (OpenWebText)

python eval.py \
    --config configs/training_configs/train_owt_ELF-B.yml \
    --checkpoint_path embedded-language-flows/ELF-B-owt

Conditional Generation (Summarization/Translation)

# XSum (summarization)
python eval.py \
    --config configs/training_configs/train_xsum_ELF-B.yml \
    --checkpoint_path embedded-language-flows/ELF-B-xsum

# WMT14 De-En (translation)
python eval.py \
    --config configs/training_configs/train_de-en_ELF-B.yml \
    --checkpoint_path embedded-language-flows/ELF-B-de-en

Citation

@article{elf2026,
  title={ELF: Embedded Language Flows},
  author={Hu, Keya and Qiu, Linlu and Lu, Yiyang and Zhao, Hanhong and Li, Tianhong and Kim, Yoon and Andreas, Jacob and He, Kaiming},
  journal={arXiv preprint arXiv:2605.10938},
  year={2026}
}