Michael Tschannen's picture

9 7

Michael Tschannen

mitsch

·

https://mitscha.github.io

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

google/siglip2-base-patch16-224:mportError: cannot import name 'Siglip2VisionModel' from 'transformers' (/home/AAA/.conda/envs/internvl/lib/python3.9/site-packages/transformers/__init__.py)

new activity about 1 month ago

google/siglip2-base-patch16-384:What parameters are fine-tuned for siglip2 using catseg's line for Open-Vocabulary semantic segmentation in this paper?

new activity about 2 months ago

google/siglip2-so400m-patch16-naflex:What is the max image resolution?

View all activity

Organizations

mitsch's activity

upvoted 2 articles 3 months ago

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

By

and 3 others •

Mar 4

• 74

Article

SigLIP 2: A better multilingual vision language encoder

By

and 2 others •

Feb 21

• 164

upvoted a collection 3 months ago

SigLIP2

36 items • Updated 4 days ago • 74

upvoted a paper 3 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 144

upvoted a collection 3 months ago

PaliGemma 2 Mix

13 items • Updated 4 days ago • 62

upvoted a paper over 1 year ago

GIVT: Generative Infinite-Vocabulary Transformers

Paper • 2312.02116 • Published Dec 4, 2023 • 13

upvoted a paper almost 2 years ago

Image Captioners Are Scalable Vision Learners Too

Paper • 2306.07915 • Published Jun 13, 2023 • 11