Update README.md

README.md

@@ -135,8 +135,9 @@ base_model:
 * **Bilingual support (Korean & English)** in a single model   -->
 
 ## 📖 Model Architecture
-
 🚀 **FastSLM-ASR** is an **Automatic Speech Recognition (ASR)-specialized model** designed for efficient speech-to-text transcription.  
+> 🎉 **Accepted to Findings of EMNLP 2026**
+
 
 ## 📌 Key Features (Safe Version)
 
@@ -267,4 +268,15 @@ FastSLM-ASR inference requires a GPU with sufficient memory.
 | --------- | ---------------- | --------- |
 | **Inference** | NVIDIA A100 / H100 | ≥ 11.8 GB |
 
-> 💡 Using mixed precision (`bfloat16`) is recommended to reduce memory usage.
+> 💡 Using mixed precision (`bfloat16`) is recommended to reduce memory usage.
+
+## 📖 Citation
+
+```bibtex
+@inproceedings{lee2026fastslm,
+  title     = {FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation},
+  author    = {Lee, Junseok and Chun, Chang-Jae},
+  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
+  year      = {2026}
+}
+```