Senqiao/LLaVA-OneVision-1.5-4B-Continue-Ultra-Mid-Training-LR-3e-5_56k-QuickSFT Image-Text-to-Text • 5B • Updated 3 days ago • 62
Senqiao/LLaVA-OneVision-1.5-4B-Continue-Ultra-Mid-Training-LR-3e-5_56k-QuickSFT Image-Text-to-Text • 5B • Updated 3 days ago • 62
Senqiao/LLaVA-OneVision-1.5-4B-OfficialMidTrain-QuickStart-SFT Image-Text-to-Text • 5B • Updated 3 days ago • 46
Senqiao/LLaVA-OneVision-1.5-4B-OfficialMidTrain-QuickStart-SFT Image-Text-to-Text • 5B • Updated 3 days ago • 46
Senqiao/CoTrain_VL0_5_Robocasa_BS32_starvla_qwen2.5OFT_fourier_gr1_unified_1000_4B Updated 7 days ago
Senqiao/CoTrain_VL0_1_Robocasa_BS32_starvla_qwen2.5OFT_fourier_gr1_unified_1000_4B Updated 7 days ago
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence Paper • 2602.08683 • Published 17 days ago • 49