Collections of ICLR 2026 paper: "OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models"
Zekun Qi
qizekun
AI & ML interests
Embodied Intelligence, Large Langugae Model, 3D Computer Vision
Recent Activity
liked a model about 9 hours ago
zbzzbz/DeFI upvoted a collection about 9 hours ago
DeformGen upvoted a collection about 9 hours ago
ImageWAMOrganizations
models 6
qizekun/PointSO
Updated • 5
qizekun/ReConV2
Updated • 3
qizekun/ShapeLLM_13B_general_v1.0
Text Generation • Updated • 36 • 1
qizekun/ShapeLLM_7B_general_v1.0
Text Generation • Updated • 49 • 2
qizekun/ShapeLLM_13B_gapartnet_v1.0
Text Generation • Updated • 11
qizekun/ShapeLLM_7B_gapartnet_v1.0
Text Generation • Updated • 23