Update README.md

README.md

@@ -6,11 +6,11 @@ pipeline_tag: text-generation
 tags:
 - reasoning
 - looped transformer
-arxiv: 2510.03215
+arxiv: 2511.08577
 library_name: transformers
 ---
 
-This is the general-trained version of TaH-plus-1.7B, presented in the paper [Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models](https://huggingface.co/papers/2511.08577).
+This is the general version of TaH-plus-1.7B, trained on a mixture of math, code, and science data, presented in the paper [Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models](https://huggingface.co/papers/2511.08577).
 
 Think-at-Hard(TaH0 uses a neural decider to dynamically initiate latent iterations only where needed. Compared with baselines that iterate twice for all output tokens, TaH delivers 8.1-11.3% accuracy gains while exempting 94% of tokens from the second iteration. Against strong single-iteration Qwen3 models finetuned with the same data, it also delivers 4.0-5.0% accuracy gains. When allowing less than 3% additional parameters from LoRA and the iteration decider, the gains increase to 8.5-12.6% and 5.3-5.4%, respectively.