gsarch/GGR-raw-human-gaze-dataset
Viewer • Updated • 7.11k • 11
GGR
Models and data for Gaze Guided Reasoner
-
-
gsarch/GGR-RL-Data
Viewer • Updated • 140k • 39 -
gsarch/Gaze-SFT
Viewer • Updated • 151k • 13 -
gsarch/Qwen3-VL-8B-GGR-RL
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-GGR-SFT
Image-Text-to-Text • 9B • Updated • 14 -
gsarch/Qwen3-VL-8B-No-Gaze-RL
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-No-Gaze-SFT
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-Fix-All-SFT
Image-Text-to-Text • 9B • Updated • 13 -
gsarch/Qwen3-VL-8B-Raw-Gaze-SFT
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-Fix-Subset-SFT
Image-Text-to-Text • 9B • Updated • 13 -
gsarch/Qwen3-VL-8B-Point-Grounded-RL
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-Ungrounded-RL
Image-Text-to-Text • 9B • Updated • 13 -
gsarch/Qwen3-VL-8B-Raw-Gaze-RL
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-Fix-All-RL
Image-Text-to-Text • 9B • Updated • 12 -
gsarch/Qwen3-VL-8B-Fix-Subset-RL
Image-Text-to-Text • 9B • Updated • 13 -
gsarch/MiMo-VL-7B-Raw-Gaze-SFT
Image-Text-to-Text • 8B • Updated • 12 -
gsarch/MiMo-VL-7B-Fix-All-SFT
Image-Text-to-Text • 8B • Updated • 13 -
gsarch/MiMo-VL-7B-Fix-Subset-SFT
Image-Text-to-Text • 8B • Updated • 12 -
gsarch/MiMo-VL-7B-GGR-SFT
Image-Text-to-Text • 8B • Updated • 12 -
gsarch/Gemma-3-4B-GGR-SFT
Image-Text-to-Text • 4B • Updated • 12 -
gsarch/Gemma-3-4B-Fix-All-SFT
Image-Text-to-Text • 4B • Updated • 12 -
gsarch/Gemma-3-4B-Fix-Subset-SFT
Image-Text-to-Text • 4B • Updated • 12