GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 7 days ago • 46
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published 7 days ago • 59
Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts Paper • 2608.00574 • Published 12 days ago • 8
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF Image-Text-to-Text • 35B • Updated 3 days ago • 436k • 480