Update README.md

README.md

@@ -1,8 +1,11 @@
+---
+license: mit
+---
 Bayesian Enhancement Model (BEM)
 
-AAAI 2026 — One-to-Many Modeling for Low-Light & Underwater Image Enhancement
-📄 Paper
- | 💻 Code
+AAAI 2026 — Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement
+Paper: arxiv:2501.14265
+Github: 
 
 🌟 Overview
 
@@ -29,38 +32,3 @@ This makes BEM the first practical Bayesian solution for large-scale image enhan
 
 BEM samples weights from a variational posterior learned by a Bayesian UNet.
 Each sample produces a distinct enhancement, capturing the ambiguity of the task 
-
-BNN_AAAI
-
-.
-
-✓ Two-Stage BNN → DNN Framework (Fast!)
-
-The core bottleneck is heavy BNN inference.
-So we introduce a coarse-to-fine pipeline:
-
-Stage I (BNN): Predict coarse latent results in low-dimensional space
-
-Stage II (DNN): Refine structural & texture details
-
-This yields a 22× speedup vs. vanilla BNNs (Fig.5 in paper) 
-
-BNN_AAAI
-
-.
-
-✓ Adaptive Prior for Stable Training
-
-Using EMA-updated parameters as priors accelerates convergence and reduces KL instability (Eq.6) 
-
-BNN_AAAI
-
-.
-
-✓ Two Inference Modes
-
-BEMRank — Select the best candidate using CLIP-IQA, NIQE, UIQM, or UCIQE
-
-BEMMC — Average multiple samples for stable, noise-free output
-
-Both modes outperform deterministic baselines.