Cite
Notes
Only stored in your browser.
Attribution
Zero-shot World Models Are Developmentally Efficient Learners
arXiv 2026
3D Scene Understanding Through Local Random Access Sequence Modeling
arXiv 2025
Discovering and using Spelke segments
Taming generative video models for zero-shot optical flow extraction
from 4 papers
Klemen Kotar
Daniel L. K. Yamins
Jared Watrous
Khai Loong Aw
Seungwoo Kim
Honglin Chen
Lilian Naing Chen
Rahul Venkatesh
Stefan Stojanov
Ashley Xu