The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models Paper • 2505.22617 • Published 9 days ago • 116
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions Paper • 2412.08737 • Published Dec 11, 2024 • 54
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness Paper • 2405.17220 • Published May 27, 2024 • 1