AAAlexxx111 commited on
Commit
ab7918b
·
verified ·
1 Parent(s): 4cb4d8d

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +10 -11
README.md CHANGED
@@ -14,11 +14,8 @@ library_name: transformers
14
  <a href="https://sjtu-deng-lab.github.io/LightningRL">
15
  <img src="https://img.shields.io/badge/Website-LightningRL-purple.svg" alt="ICML 2026"/>
16
  </a>
17
- <a href="#">
18
- <img src="https://img.shields.io/badge/arXiv-coming%20soon-b31b1b.svg" alt="Paper on arXiv"/>
19
- </a>
20
- <a href="https://sjtu-deng-lab.github.io/LightningRL/paper/LightningRL.pdf">
21
- <img src="https://img.shields.io/badge/Paper-PDF-2b6cb0.svg?logo=adobeacrobatreader&logoColor=white" alt="Paper PDF"/>
22
  </a>
23
  <a href="https://github.com/SJTU-DENG-Lab/LightningRL">
24
  <img src="https://img.shields.io/badge/GitHub-Code-black.svg?logo=github" alt="GitHub Code"/>
@@ -49,11 +46,13 @@ We introduce **LightningRL**, a reinforcement learning post-training framework f
49
  # Citation
50
 
51
  ```bibtex
52
- @article{hu2026lightningrl,
53
- title={LightningRL: Breaking the Accuracy--Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning},
54
- author={Hu, Yanzhe and Jin, Yijie and Liu, Pengfei and Yu, Kai and Deng, Zhijie},
55
- journal={arXiv preprint},
56
- year={2026},
57
- note={Coming soon}
 
 
58
  }
59
  ```
 
14
  <a href="https://sjtu-deng-lab.github.io/LightningRL">
15
  <img src="https://img.shields.io/badge/Website-LightningRL-purple.svg" alt="ICML 2026"/>
16
  </a>
17
+ <a href="https://arxiv.org/abs/2603.13319">
18
+ <img src="https://img.shields.io/badge/arXiv-Paper-b31b1b.svg" alt="Paper on arXiv"/>
 
 
 
19
  </a>
20
  <a href="https://github.com/SJTU-DENG-Lab/LightningRL">
21
  <img src="https://img.shields.io/badge/GitHub-Code-black.svg?logo=github" alt="GitHub Code"/>
 
46
  # Citation
47
 
48
  ```bibtex
49
+ @misc{hu2026lightningrlbreakingaccuracyparallelismtradeoff,
50
+ title={LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning},
51
+ author={Yanzhe Hu and Yijie Jin and Pengfei Liu and Kai Yu and Zhijie Deng},
52
+ year={2026},
53
+ eprint={2603.13319},
54
+ archivePrefix={arXiv},
55
+ primaryClass={cs.LG},
56
+ url={https://arxiv.org/abs/2603.13319},
57
  }
58
  ```