Update README.md

README.md

@@ -11,7 +11,7 @@ We introduce MMaDA, a novel class of multimodal diffusion foundation models desi
 2. MMaDA introduces a mixed long chain-of-thought (CoT) fine-tuning strategy that curates a unified CoT format across modalities.
 3. MMaDA adopts a unified policy-gradient-based RL algorithm, which we call UniGRPO, tailored for diffusion foundation models. Utilizing diversified reward modeling, UniGRPO unifies post-training across both reasoning and generation tasks, ensuring consistent performance improvements.
 
-Compared to MMaDA-8B-Base, MMaDA-8B-MixCoT exhibits better instruction-following capabilities and more stable CoT generation performance.
+Compared to [MMaDA-8B-Base](https://huggingface.co/Gen-Verse/MMaDA-8B-Base), MMaDA-8B-MixCoT exhibits better instruction-following capabilities and more stable CoT generation performance.
 
 [Paper](https://arxiv.org/abs/2505.15809) | [Code](https://github.com/Gen-Verse/MMaDA) | [Demo](https://huggingface.co/spaces/Gen-Verse/MMaDA)