SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
•
2502.14786
•
Published
•
99
Olivier Henaff
olivierhenaff
AI & ML interests
None yet
Recent Activity
authored
a paper
8 months ago
PaliGemma: A versatile 3B VLM for transfer
authored
a paper
about 1 year ago
Memory Consolidation Enables Long-Context Video Understanding
Organizations
None yet
olivierhenaff's activity
authored
a
paper
2 days ago
authored
a
paper
8 months ago
authored
a
paper
about 1 year ago
updated
a
model
over 1 year ago