Adapted DINOv2 generalises better than task-specific medical segmentation nets
Only a small part of DINOv2 was adapted; in-distribution U-Nets stayed sharper and caught small lesions more often.
46
- Mentions · 7d2
- Mentions · 30d8
- All mentions14
- First seenSep 16, 2026
- Last mentioned1d ago
Timeline
14 articles · newest firstVisual similarity partly explains adult and model word extension
DINOv2 distance tracked adult extension, and an artificial learner was less accurate for farther category pairs.
18
SIFR fuses CLIP and DINOv2 spectrally for domain-general segmentation
The method filters domain-sensitive responses at fusion and stabilizes multi-scale decoder features before dense prediction.
28
Paper turns the Platonic Representation Hypothesis into a JEPA theorem
A 109M-parameter text JEPA beat language models up to 72B on alignment with DINOv2 and CLIP image encoders.
48
Flownomaly recovers normal features for few-shot anomaly detection
In the 1-shot setting, image-level AUROC reached 97.8% on MVTec-AD and 95.3% on VisA.
36
Velocity Ambiguity Profiles split flow-matching loss by interpolation time
Guided time sampling cuts DINOv2 feature velocity loss 6.78% and Fréchet distance 23.6%, with no class-conditional KID gain.
36
Paper generates 3D scenes in implicit latents from 2D models
Diffusion transformers model scenes in a 3D latent from DINOv2, SigLIP2, and DA3 instead of redundant 2D views.
34
Generative Representation Learning for Scalable Latent Tokenization
A generative tokenizer avoids representation collapse and reaches FID-50K 2.18 with JiT-L.
46
Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Label-only backdoor audit shows feature space, not the detector score, decides whether retraining removes the attack.
48
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
A recurrent vision Transformer matches full-depth accuracy with one block and about 70% fewer parameters.
40
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
A recurrent vision Transformer matches full-depth encoder accuracy with about 70% fewer stored parameters.
48
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
PixelDense separates semantic and geometric alignment teachers, improving pixel diffusion quality and training speed.
48
First Agentic AI Data Breach Reported to Spanish Regulator
Spain's AEPD reported the first data breach executed by an AI agent, which autonomously chained login, vulnerability discovery, and personal data modification.
66
Canadian Start-up smartARM Uses AI to Create Intuitive Bionic Prosthetics
Toronto startup smartARM built a bionic prosthetic arm using Meta's DINOv2 vision model and AI glasses to automatically select grips for objects.
22
Appears with
- CLIPai model · 3
- smartARMorganization · 2
- DeiT IIIai model · 2
- Meta AI Glassesproduct · 2
- reViT-B/16ai model · 2
- DA3ai model · 1
- smartARMvendor · 1
- SAM2ai model · 1
- CyberVerseorganization · 1
- DINOai model · 1
- Depth Anything v2ai model · 1
- ResNet-32ai model · 1
- CyberVersevendor · 1
- GPICproduct · 1
- LeJEPAai model · 1
- JiT-Lai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.