Add pipeline tag, link to paper and code

README.md

@@ -1,3 +1,24 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: graph-ml
+---
+
+# Regularized Langevin Dynamics for Combinatorial Optimization
+
+This repository contains the official implementation for the paper [Regularized Langevin Dynamics for Combinatorial Optimization](https://huggingface.co/papers/2502.00277), presented at ICML 2025.
+
+The paper proposes Regularized Langevin Dynamics (RLD), a simple yet effective sampling framework for combinatorial optimization (CO). RLD enhances discrete Langevin dynamics by enforcing an expected distance between sampled and current solutions, thereby avoiding local minima. This framework develops two CO solvers: a simulated annealing approach (RLSA) and a neural network-based approach (RLNN).
+
+For more details on the implementation and usage, please refer to the official [GitHub repository](https://github.com/Shengyu-Feng/RLD4CO).
+
+## Citation
+If you find our work helpful or inspiring, please feel free to cite it:
+```bibtex
+@inproceedings{feng2025regularizedlangevindynamicscombinatorial,
+  title={Regularized Langevin Dynamics for Combinatorial Optimization}, 
+  author={Shengyu Feng and Yiming Yang},
+  booktitle={International conference on machine learning},
+  year={2025},
+  organization={PMLR}
+}
+```