VPPO Data Official training and evaluation datasets for the VPPO project. chamber111/VPPO_ViRL39K_train Viewer • Updated Oct 16, 2025 • 38.9k • 207 • 1 chamber111/VPPO_MMK12_validation Viewer • Updated Oct 16, 2025 • 2k • 228 • 1 chamber111/VPPO-Eval Preview • Updated Oct 16, 2025 • 652 • 1 Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
VPPO Model SOTA models for multimodal reasoning, fine-tuned with VPPO. Achieves superior performance by focusing on critical visual tokens. chamber111/VPPO-7B Image-Text-to-Text • 8B • Updated Nov 7, 2025 • 20 • 6 chamber111/VPPO-32B 33B • Updated Oct 16, 2025 • 14 • 2 Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37 chamber111/VPPO-8B Image-Text-to-Text • 9B • Updated Nov 7, 2025 • 39 • 2
Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
VPPO Data Official training and evaluation datasets for the VPPO project. chamber111/VPPO_ViRL39K_train Viewer • Updated Oct 16, 2025 • 38.9k • 207 • 1 chamber111/VPPO_MMK12_validation Viewer • Updated Oct 16, 2025 • 2k • 228 • 1 chamber111/VPPO-Eval Preview • Updated Oct 16, 2025 • 652 • 1 Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
VPPO Model SOTA models for multimodal reasoning, fine-tuned with VPPO. Achieves superior performance by focusing on critical visual tokens. chamber111/VPPO-7B Image-Text-to-Text • 8B • Updated Nov 7, 2025 • 20 • 6 chamber111/VPPO-32B 33B • Updated Oct 16, 2025 • 14 • 2 Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37 chamber111/VPPO-8B Image-Text-to-Text • 9B • Updated Nov 7, 2025 • 39 • 2
Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37
