DINOv3
Collection
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
•
13 items
•
Updated
•
470
Yossi Gandelsman
yossig
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 8 hours ago
DINOv3
authored
a paper
about 2 months ago
In-Context Representation Hijacking
authored
a paper
about 1 year ago
An Empirical Study of Autoregressive Pre-training from Videos
Organizations
upvoted
a
collection
about 8 hours ago
upvoted
3
papers
over 1 year ago
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
Paper
•
2410.02762
•
Published
•
9
Interpreting the Weight Space of Customized Diffusion Models
Paper
•
2406.09413
•
Published
•
20
Interpreting the Second-Order Effects of Neurons in CLIP
Paper
•
2406.04341
•
Published
•
2