-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 17 -
hongxingli/P2R-2B
Image-Text-to-Text • 2B • Updated • 25 • 1 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 26 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 23
Hongxing Li
hongxingli
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
hongxingli/SpaceCast-Bench upvoted a paper 9 days ago
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models submitted a paper 9 days ago
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language ModelsOrganizations
None yet
-
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Paper • 2510.08531 • Published • 14 -
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 359 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 523 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 372 • 5
-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 17 -
hongxingli/P2R-2B
Image-Text-to-Text • 2B • Updated • 25 • 1 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 26 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 23
-
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Paper • 2510.08531 • Published • 14 -
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 359 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 523 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 372 • 5
models 6
hongxingli/ViSkill-Sokoban
Image-Text-to-Text • 4B • Updated • 31
hongxingli/ViSkill-FrozenLake
Image-Text-to-Text • 4B • Updated • 28
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 26 • 1
hongxingli/P2R-2B
Image-Text-to-Text • 2B • Updated • 25 • 1
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 23
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 359 • 2