Update README.md

README.md

@@ -1,8 +1,12 @@
 ---
-license: apache-2.0
+lisense : apache-2.0
 ---
-HyperConv is a TensorFlow layer combining local convolution, global hypernetwork modulation, and associative memory, designed for efficient long-context representation learning.
 
-Purpose of use: embedding / retrieval / long-context
+HyperConv is a TensorFlow layer that combines local convolution, global hypernetwork-based modulation, and associative memory, designed for efficient long-context representation learning without self-attention.
 
-First release date : 2025.12.15
+Primary use cases:
+- Embedding models
+- Retrieval and similarity search
+- Long-context sequence modeling
+
+First released: 2025-12-15 (UTC)