Update README.md

README.md

@@ -18,40 +18,30 @@ We investigate domain adaptation of MLLMs through post-training, focusing on dat
     <img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/Xsz4p6f6BVi7XqIk8eUNu.png" width="900">
 </p>
 
-### **Updates**  
+### Updates  
 - **[2024/11/29]** Released our paper.
 
 
 ## About
 
-AdaMLLM is our latest effort to enhance task generalization of (M)LLMs by scaling synthetic supervised tasks based on unsupervised contexts.
+AdaMLLM represents our latest advancement in building domain-specific foundation models through post-training on synthetic supervised tasks derived from unsupervised contexts.
 
 <p align='left'>
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/HUN3Cr66w_xpj5_c7QQaI.png" width="1000">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/R3WoJXdGsjLTfoqJ93fVI.png" width="800">
 </p>
 
 - [AdaptLLM](https://huggingface.co/papers/2309.09530)  
   We employ rule-based methods to extract tasks from domain-specific corpora, reformatting them into reading comprehension tasks for continued pre-training. Our 7B finance model outperforms domain-specific models of much larger scales, such as BloombergGPT-50B.
 
-- [Instruction Pre-Training](https://huggingface.co/papers/2406.14491)  
-  We develop a general-purpose instruction synthesizer which significantly increases task diversity for LM pre-training, outperforming vanilla pre-training in both general pre-training from scratch and domain-adaptive continual pre-training.
-
 - AdaMLLM  
-  We extend supervised task synthesis to multimodality, introducing a unified visual instruction synthesizer to extract instruction-response pairs from image-caption data. Our synthetic tasks outperform those generated by manual rules, GPT-4, and GPT-4V in improving domain-specific performance for MLLMs.
-
-Looking ahead, we envision further broadening the scope of supervised task synthesis, efficiently enhancing the general capabilities of trained models.
+  We extend supervised task synthesis to multimodality, introducing a unified visual instruction synthesizer to extract instruction-response pairs from domain-specific image-caption pairs. Our synthetic tasks outperform those generated by manual rules, GPT-4, and GPT-4V in improving domain-specific performance for MLLMs.
 
 
 ## Citation
 If you find our work helpful, please consider citing us.
-```bibtex
-@article{instructPT,
-  title={Instruction Pre-Training: Language Models are Supervised Multitask Learners},
-  author={Cheng, Daixuan and Gu, Yuxian and Huang, Shaohan and Bi, Junyu and Huang, Minlie and Wei, Furu},
-  journal={arXiv preprint arXiv:2406.14491},
-  year={2024}
-}
 
+[AdaptLLM](https://huggingface.co/papers/2309.09530)
+```bibtex
 @inproceedings{
 adaptllm,
 title={Adapting Large Language Models via Reading Comprehension},