| --- |
| base_model: mk322/LaDiR-Code-8B |
| library_name: ladir |
| pipeline_tag: text-generation |
| tags: |
| - code |
| - latent-reasoning |
| - diffusion |
| - reinforcement-learning |
| --- |
| |
| # LaDi-RL-Code-8B |
|
|
| [LaDiR-Code-8B](https://huggingface.co/mk322/LaDiR-Code-8B) further trained with reinforcement learning (**LaDi-RL**). |
| **LaDiR** (Latent Diffusion Reasoner) lets an LLM reason in a continuous latent space: a VAE compresses a reasoning |
| chain into 64 latent tokens, the LLM generates this latent block with flow matching, then decodes the answer |
| conditioned on it. LaDi-RL optimizes both the latent block and the decoded answer with execution rewards. |
|
|
| Code: [github.com/mk322/LaDiR](https://github.com/mk322/LaDiR) · Papers: [LaDiR](https://arxiv.org/abs/2510.04573), [LaDi-RL](https://arxiv.org/abs/2602.01705) |
|
|
| ```bash |
| git clone https://github.com/mk322/LaDiR && cd LaDiR && pip install -e . |
| python -m eval.generate --checkpoint mk322/LaDi-RL-Code-8B |
| ``` |
|
|
| ```bibtex |
| @article{kang2026ladirl, |
| title = {LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning}, |
| author = {Kang, Haoqiang and Zhang, Yizhe and Kuang, Nikki Lijing and Ma, Yi-An and Qin, Lianhui}, |
| journal = {arXiv preprint arXiv:2602.01705}, |
| year = {2026}, |
| url = {https://arxiv.org/abs/2602.01705} |
| } |
| |
| @inproceedings{kang2026ladir, |
| title = {LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning}, |
| author = {Kang, Haoqiang and Zhang, Yizhe and Kuang, Nikki Lijing and Majamaki, Nicklas and Jaitly, Navdeep and Ma, Yi-An and Qin, Lianhui}, |
| booktitle = {International Conference on Learning Representations (ICLR)}, |
| year = {2026}, |
| url = {https://arxiv.org/abs/2510.04573} |
| } |
| ``` |
|
|
