view article Article Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action nvidia • about 21 hours ago • 46
ch-min/Qwen2.5-VL-3B-Instruct-data_scale_exp_800k-20251114_120221 Image-Text-to-Text • 4B • Updated 2 days ago • 41
ch-min/Qwen2.5-VL-3B-Instruct-data_scale_exp_400k-20251114_120221 Image-Text-to-Text • 4B • Updated 2 days ago • 36
ch-min/NVILA-Lite-2B-DATA_SCALE_EXP_800K-20251108_180221 Image-Text-to-Text • Updated 2 days ago • 37
ch-min/NVILA-Lite-2B-DATA_SCALE_EXP_400K-20251108_180221 Image-Text-to-Text • Updated 2 days ago • 37
ch-min/Qwen2.5-VL-3B-Instruct-data_scale_exp_2m-20260109_120517 Image-Text-to-Text • 4B • Updated 2 days ago • 44
ch-min/Qwen2.5-VL-3B-Instruct-data_scale_exp_80k-20251114_120221 Image-Text-to-Text • 4B • Updated 2 days ago • 42
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models Paper • 2605.30161 • Published 5 days ago • 52
Why Far Looks Up — Data-Scale Fine-tuned Checkpoints Collection Code: https://github.com/cheolhong0916/contrastive-probing • 8 items • Updated 4 days ago