-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 18 -
hongxingli/P2R-2B
Image-Text-to-Text • 2B • Updated • 57 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 74 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 41
Hongxing Li
hongxingli
AI & ML interests
None yet
Recent Activity
updated a dataset 2 days ago
hongxingli/P2R-10k new activity 2 days ago
hongxingli/P2R-4B:Add library_name to metadata new activity 2 days ago
hongxingli/P2R-2B:Add library_name to metadataOrganizations
None yet
-
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Paper • 2510.08531 • Published • 13 -
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 44 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 150 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 185 • 5
-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 18 -
hongxingli/P2R-2B
Image-Text-to-Text • 2B • Updated • 57 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 74 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 41
-
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Paper • 2510.08531 • Published • 13 -
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 44 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 150 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 185 • 5
