Update README.md

README.md

@@ -19,18 +19,16 @@ tags:
 
 ## Introduction
 
-This is the model trained in our paper: GroupRank: A Groupwise Reranking Paradigm
-Driven by Reinforcement Learning ([📝arXiv](https://arxiv.org/pdf/2511.11653)). 
-Please refer our [🧩github repository](https://github.com/AQ-MedAI/Diver) for the usage of GroupRank-32B.
+This is the model trained in our paper: GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning  ([📝arXiv](https://arxiv.org/pdf/2511.11653)). 
+
+Please refer our  [🧩github repository](https://github.com/AQ-MedAI/Diver) for the usage of GroupRank-32B.
 
 ### Highlights
 
-## HighLights
-The Diver Retriever 4B model is a reasoning-intensive model designed to tackle the challenge of reasonIR and rader. 
-We combined data from the fields of mathematics, coding, and healthcare. 
-At the same time, we made precise matching in terms of the difficulty level of the samples, and uniquely 
-constructed negative samples corresponding to each field. Therefore, this model performs very well on the Bright LeaderBoard 
-as well as the Mteb-Medical Benchmark.
+GroupRank is a reinforcement-learning-powered reranker that breaks the traditional **“pointwise vs. listwise”** trade-off: 
+it feeds the query together with a small group of candidates to an LLM, lets the model perform within-group comparisons, and outputs individual relevance scores—combining the flexibility of pointwise scoring with the contextual awareness of listwise ranking. 
+Training is driven by GRPO and a heterogeneous reward (NDCG + distributional alignment) that keeps scores consistent across groups, while a synthetic data pipeline eliminates the need for large human-labeled sets. 
+On the reasoning-heavy BRIGHT and R2MED benchmarks, GroupRank sets new SOTA **NDCG@10 (46.8 / 52.3)** with strong generalization to classic retrieval tasks.