-
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Paper • 2511.07403 • Published • 14 -
hunarbatra/STVQA-7K
Viewer • Updated • 7.59k • 307 • 3 -
hunarbatra/SpatialThinker-3B
Image-Text-to-Text • 4B • Updated • 106 -
hunarbatra/SpatialThinker-7B
Image-Text-to-Text • 8B • Updated • 78
Hunar Batra PRO
hunarbatra
AI & ML interests
LLMs | VLMs | Reasoning | Agents
Recent Activity
liked a dataset about 22 hours ago
nvidia/PhysicalAI-VANTAGE-Bench liked a dataset about 22 hours ago
nvidia/PhysicalAI-Traffic-Anomaly-Reasoning liked a dataset 1 day ago
drive-bench/arena