Zejun Li

ZejunLi

4

·

Junction4Nako

AI & ML interests

None yet

Recent Activity

upvoted a paper 22 days ago

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

upvoted a paper 22 days ago

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

updated a dataset about 1 year ago

ZejunLi/MoVT-Eval

View all activity

Organizations

upvoted 2 papers 22 days ago

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

Paper • 2610.00559 • Published Sep 30 • 23

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

Paper • 2610.15166 • Published 27 days ago • 44

upvoted a collection about 1 year ago

AdaVaR Models

Model checkpoints for our paper: https://arxiv.org/pdf/2509.22746 • 2 items • Updated Oct 18, 2025 • 2

upvoted a paper over 1 year ago

SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users

Paper • 2504.10157 • Published Apr 14, 2025 • 17