C. Emre Karataş

emredeveloper

AI & ML interests

LLM

Recent Activity

liked a model about 9 hours ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

liked a model about 11 hours ago

Wan-AI/Wan2.1-T2V-1.3B

liked a Space about 15 hours ago

Wan-AI/Wan2.1

View all activity

Organizations

None yet

emredeveloper's activity

liked a model about 9 hours ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Text Generation • Updated 3 days ago • 1.17M • • 1.19k

liked a model about 11 hours ago

Wan-AI/Wan2.1-T2V-1.3B

Text-to-Video • Updated about 12 hours ago • 2.68k • 143

liked a Space about 15 hours ago

447

Wan2.1

💻

Wan: Open and Advanced Large-Scale Video Generative Models

upvoted an article 1 day ago

Article

FastRTC: The Real-Time Communication Library for Python

2 days ago

• 77

reacted to wassemgtk's post with 🤗🔥 1 day ago

Post

1142

# GESAL: Real-Time Adaptation for LLMs

We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like meta-llama/Llama-3.2-1B adapt in real time using user feedback. Check out the code and white paper on GitHub!

🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL)

---

## Why GESAL?

Static LLMs struggle to adapt without heavy retraining. GESAL solves this with:
- **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters.
- **Graph Memory**: Stores adaptations in nodes for scalability.
- **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback.

---

## How It Works

Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats.

---

## Try It

Built with Hugging Face’s transformers:

pip install transformers torch numpy
python Adaptive_Learning_(GESAL).py

Needs a Hugging Face token for Llama-3.2-1B.

---

## Results

GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.