add link to technical report

README.md

@@ -28,7 +28,7 @@ The model underwent a multi-phase post-training process to enhance both its reas
 
 This model is ready for commercial use. 
 
-For more details on how the model was trained, please see [this blog](https://developer.nvidia.com/blog/build-enterprise-ai-agents-with-advanced-open-nvidia-llama-nemotron-reasoning-models/).
+For more details on how the model was trained, please see our [technical report](https://arxiv.org/abs/2505.00949) and [blog](https://developer.nvidia.com/blog/build-enterprise-ai-agents-with-advanced-open-nvidia-llama-nemotron-reasoning-models/).
 
 ![Training Flow](./training_flowchart.png)
 
@@ -55,6 +55,7 @@ Developers designing AI Agent systems, chatbots, RAG systems, and other AI-power
 
 ## References
 
+* [\[2505.00949\] Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)
 * [\[2502.00203\] Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment](https://arxiv.org/abs/2502.00203)  
 * [\[2411.19146\]Puzzle: Distillation-Based NAS for Inference-Optimized LLMs](https://arxiv.org/abs/2411.19146)  
 * [\[2503.18908\]FFN Fusion: Rethinking Sequential Computation in Large Language Models](https://arxiv.org/abs/2503.18908)