Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions Paper • 2412.08737 • Published Dec 11, 2024 • 53
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness Paper • 2405.17220 • Published May 27, 2024 • 1