multimodal-r1

Here are 4 public repositories matching this topic...

Solve Visual Understanding with Reinforced VLMs

reinforcement-learning vlm multimodal llm qwen deepseek-r1 grpo r1-zero vlm-r1 multimodal-r1

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

reinforcement-learning reasoning vlm llm multimodal-understanding deepseek-r1 grpo vlm-r1 multimodal-r1 r1v skywork-r1v

Explore the Multimodal “Aha Moment” on 2B Model

Proposed fuzzy reward model with GRPO to improve VLM's abilities in crowd counting task.

reinforcement-learning vlm crowdcounting llm reward-model r1-zero vlm-r1 multimodal-r1

To associate your repository with the multimodal-r1 topic, visit your repo's landing page and select "manage topics."