 |
VOOZH | about |
[CVPR 2026 Official Implementation] Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
A reinforcement learning agent that learns to solve mazes using Group Relative Policy Optimization (GRPO).
Fine-tuning Qwen2.5-VL-3B-Instruct to output high quality chain-of-thoughts on GQA dataset with reinforcement learning
A simple and explained implementation of (Dr.) GRPO in PyTorch.
Bachelor thesis codebase: GRPO training for improving mathematical reasoning in small language models using reinforcement learning
Fine-tuning Qwen2.5-3B-Instruct model with LoRa (Low-Rank Adaptation) and Group Relative Policy Optimization (GRPO)
Fine-tune a model that generates exams based on lecture materials.
Add a description, image, and links to the group-relative-policy-optimization topic page so that developers can more easily learn about it.
To associate your repository with the group-relative-policy-optimization topic, visit your repo's landing page and select "manage topics."