Thank you for the great article. It was very informative and well-organized> I wonder why there was no mention of InternVL. When comparing smaller VLM, InternVL does pretty well afaik.
Niloofar Zarif
nzarif
·
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
OpenGVLab/InternVL3-2B:Max num tiles > 1 for video data
new activity
about 2 months ago
nvidia/omnivinci:Model variations
commented on
an
article
7 months ago
Vision Language Models (Better, faster, stronger)
Organizations
None yet
Max num tiles > 1 for video data
#5 opened about 1 month ago
by
nzarif
Model variations
#1 opened about 2 months ago
by
nzarif
commented on
Vision Language Models (Better, faster, stronger)
7 months ago
upvoted
an
article
7 months ago
Article
Vision Language Models (Better, faster, stronger)
- +3
•
568