Maijunxian Wang's picture

Maijunxian Wang

Mark7121983123

·

https://mjxwang.github.io/Maijunxian-Wang-s-Personal-Website-1-/

AI & ML interests

None yet

Recent Activity

upvoted a paper about 5 hours ago

Vision Language Models Cannot Reason About Physical Transformation

upvoted a paper about 5 hours ago

Demystifing Video Reasoning

upvoted a paper 1 day ago

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

View all activity

Organizations

upvoted 2 papers about 5 hours ago

Vision Language Models Cannot Reason About Physical Transformation

Paper • 2603.07109 • Published 11 days ago • 1

Demystifing Video Reasoning

Paper • 2603.16870 • Published about 14 hours ago • 50

upvoted a paper 1 day ago

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

Paper • 2603.15612 • Published 1 day ago • 92

upvoted an article 9 days ago

Article

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

13 days ago

•

98

upvoted 2 collections 12 days ago

AI Paper of the Day

A collection of papers that I think are interesting, one added each day • 619 items • Updated 1 day ago • 91

SenseNova-SI

Scaling Spatial Intelligence with Multimodal Foundation Models • 10 items • Updated Jan 11 • 16

upvoted a paper 13 days ago

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

Paper • 2603.04338 • Published 14 days ago • 24

upvoted a collection 13 days ago

VBVR: A Very Big Video Reasoning Suite

6 items • Updated 15 days ago • 4

upvoted a collection 19 days ago

papers

42 items • Updated 1 day ago • 2

upvoted 2 papers 22 days ago

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

Paper • 2512.19693 • Published Dec 22, 2025 • 67

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 23 days ago • 514