8 18 42

Zekun Qi

qizekun

https://qizekun.github.io/

qizekun

AI & ML interests

3D Computer Vision, MLLM

Recent Activity

liked a Space about 15 hours ago

facebook/vggt

updated a dataset 4 days ago

qizekun/OmniSpatial

liked a model 6 days ago

remyxai/SpaceQwen2.5-VL-3B-Instruct

View all activity

Organizations

qizekun's activity

liked a Space about 15 hours ago

200

vggt

🏆

VGGT (CVPR 2025)

updated a dataset 4 days ago

qizekun/OmniSpatial

Viewer • Updated 4 days ago • 1.39k • 401 • 5

liked a model 6 days ago

remyxai/SpaceQwen2.5-VL-3B-Instruct

Image-Text-to-Text • Updated 1 day ago • 90.4k • 13

New activity in qizekun/OmniSpatial 7 days ago

Add link to paper

#3 opened 7 days ago by

nielsr

Update task category and add Github link

#2 opened 8 days ago by

nielsr

authored a paper 10 days ago

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

Paper • 2506.03135 • Published 10 days ago • 37

upvoted a paper 10 days ago

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

Paper • 2506.03135 • Published 10 days ago • 37

commented a paper 10 days ago

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

Paper • 2506.03135 • Published 10 days ago • 37 •

upvoted a paper 10 days ago

ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

Paper • 2506.01853 • Published 12 days ago • 28

upvoted a paper 12 days ago

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

Paper • 2505.24863 • Published 14 days ago • 91

liked a dataset 30 days ago

qizekun/OmniSpatial

Viewer • Updated 4 days ago • 1.39k • 401 • 5

liked a Space about 1 month ago

1.5k

InstantMesh

📚

Create a 3D model from an image in 10 seconds!

upvoted a paper about 2 months ago

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published Apr 24 • 88

liked a dataset about 2 months ago

JeffreyXiang/TRELLIS-500K

Viewer • Updated Dec 26, 2024 • 504k • 1.13k • 36

published a dataset about 2 months ago

qizekun/OmniSpatial

Viewer • Updated 4 days ago • 1.39k • 401 • 5

upvoted a paper 2 months ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published Apr 7 • 105

liked a model 3 months ago

stabilityai/stable-virtual-camera

Image-to-Video • Updated 10 days ago • 45.6k • 202

liked a dataset 3 months ago

Battam/3D-CoT

Viewer • Updated Mar 14 • 145k • 106 • 2

upvoted a collection 3 months ago

DreamLLM

Collection

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation (https://arxiv.org/abs/2309.11499) • 6 items • Updated Mar 22, 2024 • 3

upvoted a paper 3 months ago

Unleashing Vecset Diffusion Model for Fast Shape Generation

Paper • 2503.16302 • Published Mar 20 • 44