-
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Paper • 2511.07403 • Published • 14 -
hunarbatra/STVQA-7K
Viewer • Updated • 7.59k • 403 • 2 -
hunarbatra/SpatialThinker-3B
Image-Text-to-Text • 4B • Updated • 51 -
hunarbatra/SpatialThinker-7B
Image-Text-to-Text • 8B • Updated • 26
Hunar Batra
hunarbatra
AI & ML interests
LLMs | VLMs | Reasoning | Agents
Recent Activity
updated a dataset about 17 hours ago
hunarbatra/4DReasoner_v3_full published a dataset about 17 hours ago
hunarbatra/4DReasoner_v3_full updated a dataset about 17 hours ago
hunarbatra/4DReasoner_v3_part4Organizations
-
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Paper • 2511.07403 • Published • 14 -
hunarbatra/STVQA-7K
Viewer • Updated • 7.59k • 403 • 2 -
hunarbatra/SpatialThinker-3B
Image-Text-to-Text • 4B • Updated • 51 -
hunarbatra/SpatialThinker-7B
Image-Text-to-Text • 8B • Updated • 26