Update README.md
Browse files
README.md
CHANGED
|
@@ -89,6 +89,9 @@ Samples processed by LLaSE-G1 can be found on our [Demo Page](https://submission
|
|
| 89 |
|
| 90 |
Our pretrained model is available on [Hugging Face](https://huggingface.co/ASLP-lab/LLaSE-G1).
|
| 91 |
|
|
|
|
|
|
|
|
|
|
| 92 |
## Citation
|
| 93 |
|
| 94 |
If you find this work useful, please cite our paper:
|
|
|
|
| 89 |
|
| 90 |
Our pretrained model is available on [Hugging Face](https://huggingface.co/ASLP-lab/LLaSE-G1).
|
| 91 |
|
| 92 |
+
## Hints
|
| 93 |
+
Our approach focuses on leveraging the LLM's comprehension capabilities to enable autonomous determination of task types, though this may exhibit instability in certain scenarios. A more stable and robust iteration will be released in the upcoming version.
|
| 94 |
+
|
| 95 |
## Citation
|
| 96 |
|
| 97 |
If you find this work useful, please cite our paper:
|