Maijunxian Wang

Mark7121983123's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 14 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 14 days ago • 366

upvoted 2 papers 14 days ago

Vision Language Models Cannot Reason About Physical Transformation

Paper • 2603.07109 • Published 25 days ago • 1

Demystifing Video Reasoning

Paper • 2603.16870 • Published 14 days ago • 366

upvoted a paper 15 days ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 15 days ago • 151

upvoted an article 23 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

26 days ago

•

106

liked a model 25 days ago

LiconStudio/VBVR-wan2.2-comfy-bf16

Updated Feb 26 • 8.17k • 30

upvoted 2 collections 26 days ago

AI Paper of the Day

Collection

A collection of papers that I think are interesting, one added each day • 628 items • Updated about 4 hours ago • 93

SenseNova-SI

Collection

Scaling Spatial Intelligence with Multimodal Foundation Models • 13 items • Updated 5 days ago • 16

upvoted a paper 27 days ago

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Paper • 2603.04338 • Published 27 days ago • 24

upvoted a collection 27 days ago

VBVR: A Very Big Video Reasoning Suite

Collection

6 items • Updated 29 days ago • 4

updated a Space 30 days ago

Running

Video-Reason

🎬

updated a dataset about 1 month ago

Video-Reason/VBVR-Dataset

Viewer • Updated Feb 27 • 1M • 2.03k • 50

upvoted a collection about 1 month ago

papers

Collection

42 items • Updated 15 days ago • 2

liked a Space about 1 month ago

Running

2

AI Deadlines

⚡

2

Find upcoming AI conference deadlines in one place

liked a dataset about 1 month ago

Video-Reason/VBVR-Dataset

Viewer • Updated Feb 27 • 1M • 2.03k • 50

authored a paper about 1 month ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 517

upvoted a paper about 1 month ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published Dec 22, 2025 • 67

liked a dataset about 1 month ago

Video-Reason/VBVR-Bench-Data

Viewer • Updated Feb 24 • 500 • 1.15k • 8

liked a model about 1 month ago

Video-Reason/VBVR-Wan2.2

Image-to-Video • Updated 29 days ago • 370 • 123

liked a Space about 1 month ago

Running

12

VBVR Bench Leaderboard

🥇

12

Leaderboard for VBVR-Bench