Enabling Versatile Controls for Video Diffusion Models Paper • 2503.16983 • Published Mar 21, 2025 • 15
PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks Paper • 2503.04065 • Published Mar 6, 2025
PaddlePaddle/PaddleOCR-VL Image-Text-to-Text • 1.0B • Updated about 1 month ago • 7.65k • 1.63k
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Paper • 2509.02547 • Published Sep 2, 2025 • 239
view article Article From GRPO to DAPO and GSPO: What, Why, and How NormalUhr • Aug 9, 2025 • 128
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle Image-Text-to-Text • 424B • Updated Aug 19, 2025 • 19 • 68