diff --git a/examples/benchmarks/SFM/README.md b/examples/benchmarks/SFM/README.md
index 06ca50485..eb1c8b157 100644
--- a/examples/benchmarks/SFM/README.md
+++ b/examples/benchmarks/SFM/README.md
@@ -1,4 +1,4 @@
 # State-Frequency-Memory
-- State Frequency Memory (SFM) is a novel recurrent network that uses Discrete Fourier Transform (DFT) to decompose the hidden states of memory cells and capture the multi-frequency trading patterns from past market data to make stock price predictions. 
-- The code used in Qlib is a pyTorch implementation of SFM (Zhang, L., Aggarwal, C., & Qi, G. J. (2017,)).
-- Paper: Stock Price Prediction via Discovering Multi-Frequency Trading Patterns. https://www.cs.ucf.edu/~gqi/publications/kdd2017_stock.pdf.
\ No newline at end of file
+- State Frequency Memory (SFM) is a novel recurrent network that uses Discrete Fourier Transform to decompose the hidden states of memory cells and capture the multi-frequency trading patterns from past market data to make stock price predictions. 
+- The code used in Qlib is a pyTorch implementation of SFM.
+- Paper: Stock Price Prediction via Discovering Multi-Frequency Trading Patterns. [https://www.cs.ucf.edu/~gqi/publications/kdd2017_stock.pdf.](https://www.cs.ucf.edu/~gqi/publications/kdd2017_stock.pdf.)
\ No newline at end of file