Cite
Notes
Only stored in your browser.
Attribution
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
arXiv 2025
Adaptive Token Sampling For Efficient Vision Transformers
arXiv 2021
from 2 papers
Mohsen Fayyaz
Dimitrios Mallios
Eric Sommerlade
Faegheh Sardari
Farnoush Rezaei Jafari
Gedas Bertasius
Hamed Pirsiavash
Hamid Reza Vaezi Joze
Juergen Gall
Parth Pathak