Afshin Dehghan
- Papers
- 6
Cite
Notes
Only stored in your browser.
6papers
Authored papers
6VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
arXiv 2026
(1D) Ordered Tokens Enable Efficient Test-Time Search
arXiv 2026
MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
arXiv 2025
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
arXiv 2024
4M: Massively Multimodal Masked Modeling
4m-massively-multimodal-masked-modeling
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data
arXiv 2021
Affiliations
No known affiliations.
Frequent co-authors
10from 6 papers