Add pipeline tag and improve model card

README.md

@@ -1,14 +1,16 @@
 ---
-license: apache-2.0
+base_model:
+- TinyLlama/TinyLlama_v1.1
 datasets:
 - HuggingFaceFW/fineweb-edu
+license: apache-2.0
 model_name: TinyLlama_v1.1_LoopUS
-base_model:
-- TinyLlama/TinyLlama_v1.1
 tags:
 - LoopUS
 - LoopedTransformers
+pipeline_tag: text-generation
 ---
+
 <div align="center">
 <h1>LoopUS: <br> Recasting Pretrained LLMs into Looped Latent Refinement Models</h1>
 </div>
@@ -26,18 +28,20 @@ tags:
 </p>
 
 <p align="center">
-  <a href="https://thrillcrazyer.github.io/LoopUS"><b>🌟 Github</b></a> |
-  <a href="https://huggingface.co/Thrillcrazyer/Qwen3_1.7B_LoopUS"><b>📥 Download</b></a> |
+  <a href="https://github.com/Thrillcrazyer/LoopUS"><b>🌟 Github</b></a> |
+  <a href="https://thrillcrazyer.github.io/LoopUS"><b>🌐 Project Page</b></a> |
   <a href="https://arxiv.org/abs/2605.11011"><b>📄 Paper</b></a> 
 </p>
 
 
 # Abstract
 
-Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typically require either training recurrent models from scratch or applying disruptive retrofits, which involve substantial computational costs and may compromise pretrained capabilities. To address these limitations, we introduce \textbf{Looped Depth Up-Scaling} (LoopUS), a post-training framework that converts a standard pretrained LLM into a looped architecture. As a key technical contribution, LoopUS recasts the pretrained LLM into an encoder, a looped reasoning block, and a decoder. It operationalizes this latent-refinement architecture through four core components: (1) block decomposition, guided by staged representation dynamics; (2) an input-dependent selective gate to mitigate hidden-state drift; (3) random deep supervision for memory-efficient learning over long recursive horizons; and (4) a confidence head for adaptive early exiting. Collectively, these mechanisms transform a standard non-looped model into a looped form while stabilizing it against both computational bottlenecks and representation collapse. Through stable latent looping, LoopUS improves reasoning-oriented performance without extending the generated traces or requiring recurrent training from scratch.
+Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. We introduce **Looped Depth Up-Scaling** (LoopUS), a post-training framework that converts a standard pretrained LLM into a looped architecture. LoopUS recasts the pretrained LLM into an encoder, a looped reasoning block, and a decoder. It operationalizes this latent-refinement architecture through block decomposition, an input-dependent selective gate, random deep supervision, and a confidence head for adaptive early exiting. Through stable latent looping, LoopUS improves reasoning-oriented performance without extending the generated traces or requiring recurrent training from scratch.
 
 # QuickStart
 
+To use LoopUS, clone the repository and run the chat script:
+
 ```bash
 git clone https://github.com/Thrillcrazyer/LoopUS.git
 cd LoopUS
@@ -48,4 +52,20 @@ uv run chat.py
 
 <div align="center">
 <img src="https://raw.githubusercontent.com/Thrillcrazyer/LoopUS/main/assets/Framework.png" width="800"/>
-</div>
+</div>
+
+# Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@misc{park2026loopus,
+      title={LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models}, 
+      author={Taekhyun Park and Yongjae Lee and Dohee Kim and Hyerim Bae},
+      year={2026},
+      eprint={2605.11011},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2605.11011}, 
+}
+```