Update README.md

README.md

@@ -35,8 +35,8 @@ MATRIX-PT modifies the base model through lightweight post-training to better su
 
 ### Model Sources
 - **Repository:** https://huggingface.co/radical-ai/MATRIX-PT  
-<!-- - **Paper:** *[MATRIX: A Multimodal Benchmark and Post-Training Framework for
-Materials Science](https://www.arxiv.org/pdf/2602.00376)*   -->
+- **Paper:** *[MATRIX: A Multimodal Benchmark and Post-Training Framework for
+Materials Science](https://www.arxiv.org/pdf/2602.00376)*  
 - **Benchmark:** https://huggingface.co/datasets/radical-ai/MATRIX  
 
 ---
@@ -119,8 +119,8 @@ The adapter was trained using a curated materials science dataset emphasizing:
 - Hypothesis generation
 - Multimodal reasoning over experimental imagery
 
-<!-- For evaluation details, see the [MATRIX dataset](https://huggingface.co/datasets/radical-ai/MATRIX) card and accompanying paper.
- -->
+For evaluation details, see the [MATRIX dataset](https://huggingface.co/datasets/radical-ai/MATRIX) card and accompanying paper.
+
 ### Training Procedure
 
 - Method: LoRA (parameter-efficient fine-tuning)
@@ -147,7 +147,7 @@ Across MATRIX tasks, MATRIX-PT demonstrates improved performance relative to the
 - Interpretation of experimental images
 
 These improvements primarily manifest at inference time, highlighting the role of post-training in shaping reasoning accessibility rather than training-time memorization alone.
-<!-- 
+
 ## Citation
 
 If you use this model or the MATRIX benchmark, please cite the accompanying paper:
@@ -162,7 +162,7 @@ If you use this model or the MATRIX benchmark, please cite the accompanying pape
   journal = {arXiv preprint arXiv:2602.00376},
   year    = {2026}
 }
- -->
+
 ```
 
 ### Framework Versions