Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Sonia Joseph
Observed name:
Joseph, Sonia
Institutions:
University of Oxford,
Meta (United States),
Mila - Quebec Artificial Intelligence Institute,
McGill University
Observed institutions:
University of Oxford,
Meta (United States),
Mila - Quebec Artificial Intelligence Institute,
McGill University
OpenAlex ID:
A5124153233
Interpreting Physics in Video World Models
2026
·
Joseph, Sonia
, Garrido, Quentin
, et al.
·
arXiv (Cornell University)
·
42
PDF
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
2026
·
Xu, Junxiang
, Wang, Ruisi
, et al.
·
arXiv (Cornell University)
·
8
PDF
Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
2026
·
Qin, Chuan
, Venhoff, Constantin
, et al.
·
International Conference on Learning Representations
·
4
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
2026
·
Musa, Sharon S.
, Forghani, Fereshteh
, et al.
·
arXiv (Cornell University)
·
3
PDF
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization
2026
·
Suresh, Praneet
, Stanley, Jack
, et al.
·
arXiv (Cornell University)
·
1
PDF
Show more works
View as search
Works count:
7
Citation count:
139
H-index:
4
I10-index:
3
Year
Topic
Type