Update README.md

README.md

@@ -26,7 +26,7 @@ Our Mission: **Generative AI for all, intelligence in every task.**
 #### 🧠 Reasoning-Enhanced Low-Resource Training Pipeline
 
 - [InfiR](https://huggingface.co/papers/2502.11573): **InfiR** aims to advance AI systems by improving reasoning, reducing adoption barriers, and addressing privacy concerns through smaller model sizes. 
-- [InfiR-FP8](https://huggingface.co/InfiX-ai): **InfiR-FP8** is a smaller reasoning-enhanced model trained from scratch using FP8 precision, achieving successful convergence while reducing memory usage by 10% and improving training speed by 20% during the training process. The model will be released in mid-September.
+- [InfiR-FP8](https://huggingface.co/papers/2509.22536): **InfiR2** a fine-grained, hybrid-granularity FP8 quantization strategy to match BF16 performance while achieving up to a 22% reduction in training time and a 19% increase in throughput.
 - [InfiAlign](https://huggingface.co/papers/2508.05496): **InfiAlign** is a scalable and data-efficient post-training framework that combines supervised fine-tuning (SFT) and reinforcement learning (RL) with a high-quality data selection pipeline to enhance reasoning in large language models.
 - [InfiMMR](https://huggingface.co/papers/2505.23091): **InfiMMR** is a novel three-phase curriculum framework that systematically enhances multimodal reasoning capabilities in small language models through foundational reasoning activation, cross-modal adaptation, and multimodal reasoning enhancement.