Update README.md
Browse files
README.md
CHANGED
|
@@ -41,10 +41,6 @@ We investigate domain adaptation of MLLMs through post-training, focusing on dat
|
|
| 41 |
|
| 42 |
**Code**: [https://github.com/bigai-ai/QA-Synthesizer](https://github.com/bigai-ai/QA-Synthesizer)
|
| 43 |
|
| 44 |
-
|
| 45 |
-
## Contact
|
| 46 |
-
Daixuan Cheng: `daixuancheng6@gmail.com`
|
| 47 |
-
|
| 48 |
## About
|
| 49 |
|
| 50 |
AdaMLLM is our latest effort to enhance task generalization of (M)LLMs by scaling synthetic supervised tasks based on unsupervised contexts.
|
|
@@ -64,10 +60,14 @@ AdaMLLM is our latest effort to enhance task generalization of (M)LLMs by scalin
|
|
| 64 |
|
| 65 |
Looking ahead, we envision further broadening the scope of supervised task synthesis, efficiently enhancing the general capabilities of trained models.
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
## Citation
|
| 68 |
If you find our work helpful, please cite us.
|
| 69 |
|
| 70 |
-
[
|
| 71 |
```bibtex
|
| 72 |
@article{adamllm,
|
| 73 |
title={On Domain-Specific Post-Training for Multimodal Large Language Models},
|
|
@@ -79,7 +79,7 @@ If you find our work helpful, please cite us.
|
|
| 79 |
|
| 80 |
[Instruction Pre-Training](https://huggingface.co/papers/2406.14491) (EMNLP 2024)
|
| 81 |
```bibtex
|
| 82 |
-
@article{
|
| 83 |
title={Instruction Pre-Training: Language Models are Supervised Multitask Learners},
|
| 84 |
author={Cheng, Daixuan and Gu, Yuxian and Huang, Shaohan and Bi, Junyu and Huang, Minlie and Wei, Furu},
|
| 85 |
journal={arXiv preprint arXiv:2406.14491},
|
|
@@ -90,7 +90,7 @@ If you find our work helpful, please cite us.
|
|
| 90 |
[Adapt LLM to Domains](https://huggingface.co/papers/2309.09530) (ICLR 2024)
|
| 91 |
```bibtex
|
| 92 |
@inproceedings{
|
| 93 |
-
|
| 94 |
title={Adapting Large Language Models via Reading Comprehension},
|
| 95 |
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
|
| 96 |
booktitle={The Twelfth International Conference on Learning Representations},
|
|
|
|
| 41 |
|
| 42 |
**Code**: [https://github.com/bigai-ai/QA-Synthesizer](https://github.com/bigai-ai/QA-Synthesizer)
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## About
|
| 45 |
|
| 46 |
AdaMLLM is our latest effort to enhance task generalization of (M)LLMs by scaling synthetic supervised tasks based on unsupervised contexts.
|
|
|
|
| 60 |
|
| 61 |
Looking ahead, we envision further broadening the scope of supervised task synthesis, efficiently enhancing the general capabilities of trained models.
|
| 62 |
|
| 63 |
+
## Contact
|
| 64 |
+
Daixuan Cheng: `daixuancheng6@gmail.com`
|
| 65 |
+
|
| 66 |
+
|
| 67 |
## Citation
|
| 68 |
If you find our work helpful, please cite us.
|
| 69 |
|
| 70 |
+
[Adapt MLLM to Domains](https://huggingface.co/papers/2411.19930)
|
| 71 |
```bibtex
|
| 72 |
@article{adamllm,
|
| 73 |
title={On Domain-Specific Post-Training for Multimodal Large Language Models},
|
|
|
|
| 79 |
|
| 80 |
[Instruction Pre-Training](https://huggingface.co/papers/2406.14491) (EMNLP 2024)
|
| 81 |
```bibtex
|
| 82 |
+
@article{instructPT,
|
| 83 |
title={Instruction Pre-Training: Language Models are Supervised Multitask Learners},
|
| 84 |
author={Cheng, Daixuan and Gu, Yuxian and Huang, Shaohan and Bi, Junyu and Huang, Minlie and Wei, Furu},
|
| 85 |
journal={arXiv preprint arXiv:2406.14491},
|
|
|
|
| 90 |
[Adapt LLM to Domains](https://huggingface.co/papers/2309.09530) (ICLR 2024)
|
| 91 |
```bibtex
|
| 92 |
@inproceedings{
|
| 93 |
+
adaptllm,
|
| 94 |
title={Adapting Large Language Models via Reading Comprehension},
|
| 95 |
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
|
| 96 |
booktitle={The Twelfth International Conference on Learning Representations},
|