Update README.md

README.md

@@ -12,7 +12,7 @@ base_model: Salesforce/blip2-opt-2.7b
 ---
 # VLRM
 This repository contains the weights of BLIP-2 OPT-2.7B model fine-tuned by reinforcement learning method introduced in the paper [VLRM: Vision-Language Models act as
-Reward Models for Image Captioning (on submission ATM)](https://arxiv.org/submit/5511483/view).
+Reward Models for Image Captioning](https://arxiv.org/abs/2404.01911).
 
 The RL-tuned model is able to generate longer and more comprehensive descriptions with zero computational overhead compared to the original model.