Scholar
Jesse Allardice
Google Scholar ID: k97jb6gAAAAJ
Apple
Mutlimodal Foundation Models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
835
H-index
15
i10-index
17
Publications
20
Co-authors
0
Publications
7 items
CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?
2026
Cited
0
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
2026
Cited
0
(1D) Ordered Tokens Enable Efficient Test-Time Search
2026
Cited
0
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
2026
Cited
0
Language Models Improve When Pretraining Data Matches Target Tasks
2025
Cited
0
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
2025
Cited
0
STIV: Scalable Text and Image Conditioned Video Generation
arXiv.org · 2024
Cited
13
