Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,26 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# RespAI Lab
|
| 11 |
+
|
| 12 |
+
π Bhubaneswar, India
|
| 13 |
+
β¨ Advancing large language models through cutting-edge research.
|
| 14 |
+
|
| 15 |
+
## About Us
|
| 16 |
+
RespAI Lab, led by Dr. Murari Mandal, focuses on overcoming challenges in large language models (LLMs) like long-content processing, inference efficiency, interpretability, and alignment. We also explore synthetic persona creation, regulatory issues, model merging, knowledge verification, and unlearning techniques.
|
| 17 |
+
|
| 18 |
+
## Current Research Areas
|
| 19 |
+
- **Enhancing advanced reasoning in LLMs**: Improving complex reasoning abilities for better decision-making and contextual understanding.
|
| 20 |
+
- **Long-content processing for LLMs**: Addressing performance bottlenecks, memory limitations, and information loss.
|
| 21 |
+
- **Inference efficiency optimization**: Reducing computational costs while improving speed and memory usage.
|
| 22 |
+
- **Interpretability and alignment**: Ensuring AI models align with human values and addressing hallucination issues.
|
| 23 |
+
- **Synthetic persona and societal dynamics**: Creating and studying synthetic personalities and communities.
|
| 24 |
+
- **Regulatory challenges in LLMs**: Tackling data privacy issues and implementing unlearning techniques.
|
| 25 |
+
- **Model merging and knowledge verification**: Merging models and verifying the accuracy of generated knowledge.
|
| 26 |
+
|
| 27 |
+
## Join Us
|
| 28 |
+
Be a part of our mission to drive AI innovation! Explore our work, contribute, and collaborate with us to create meaningful advancements.
|
| 29 |
+
|
| 30 |
+
π» Visit us: [RespAI Lab Website](https://respailab.github.io/)
|
| 31 |
+
π€ Join us on Hugging Face: [RespAI Lab Organization](#)
|
| 32 |
+
|