-
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 • 20 • 1 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 20 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 22
Hongxing Li
hongxingli
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
TTPO: Test-Time Policy Optimization upvoted a paper 2 months ago
Pass the Baton: Trajectory-Relayed On-Policy Distillation updated a dataset 3 months ago
hongxingli/P2R-10kOrganizations
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 • 509 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 354 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 208 • 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 • 20 • 1 -
hongxingli/P2R-4B
Image-Text-to-Text • 5B • Updated • 20 • 1 -
hongxingli/P2R-8B
Image-Text-to-Text • 9B • Updated • 22
-
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Paper • 2510.08531 • Published • 14 -
hongxingli/SpatialLadder-3B
Image-Text-to-Text • 4B • Updated • 509 • 2 -
hongxingli/SpatialLadder-26k
Viewer • Updated • 26.6k • 354 • 5 -
hongxingli/SPBench
Viewer • Updated • 1.33k • 208 • 5
