ViGoRL - a gsarch Collection

gsarch 's Collections

ViGoRL

ViGoRL

updated Jul 24

Models from the paper "Grounded Reinforcement Learning for Visual Reasoning"

gsarch/ViGoRL-7b-Spatial

Image-Text-to-Text • 8B • Updated Jul 8 • 959 • 1
gsarch/ViGoRL-7b-Web-Grounding

Image-Text-to-Text • 8B • Updated Jun 23 • 12
gsarch/ViGoRL-7b-Web-Action

Image-Text-to-Text • 8B • Updated Jul 8 • 20
gsarch/ViGoRL-Multiturn-7b-Visual-Search

Image-Text-to-Text • 8B • Updated Jun 23 • 23
gsarch/ViGoRL-3b-Spatial

Image-Text-to-Text • 4B • Updated Jul 8 • 121 • 2
gsarch/ViGoRL-3b-Web-Action

Image-Text-to-Text • 4B • Updated Jul 8 • 17
gsarch/ViGoRL-Multiturn-3b-Visual-Search

Image-Text-to-Text • 4B • Updated Jun 23 • 11 • 1
gsarch/ViGoRL-MCTS-SFT-3b-Spatial

Image-Text-to-Text • 4B • Updated Jul 9 • 79 • 1
gsarch/ViGoRL-3b-Web-Grounding

Image-Text-to-Text • 4B • Updated Jul 14 • 8
gsarch/ViGoRL-MCTS-SFT-7b-Web-Grounding

Image-Text-to-Text • 8B • Updated Jun 23 • 10
gsarch/ViGoRL-MCTS-SFT-7b-Spatial

Image-Text-to-Text • 8B • Updated Jul 9 • 107
gsarch/ViGoRL-Multiturn-3b-Web-Grounding

Image-Text-to-Text • 4B • Updated Jun 23 • 13
gsarch/ViGoRL-MCTS-SFT-3b-Web-Grounding

Image-Text-to-Text • 4B • Updated Jun 23 • 14
gsarch/ViGoRL-Multiturn-MCTS-SFT-3b-Web-Grounding

Image-Text-to-Text • 4B • Updated Jun 23 • 8
gsarch/ViGoRL-Multiturn-MCTS-SFT-7b-Visual-Search

Image-Text-to-Text • 8B • Updated Jun 23 • 9
gsarch/ViGoRL-Multiturn-MCTS-SFT-3b-Visual-Search

4B • Updated Jun 18 • 8
Grounded Reinforcement Learning for Visual Reasoning

Paper • 2505.23678 • Published May 29 • 2