Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers
The framework helps users define subjective concepts like 'healthy food' by iteratively refining definitions using human feedback on borderline images.
40
- Mentions · 7d1
- Mentions · 30d2
- All mentions5
- First seenSep 8, 2026
- Last mentioned5d ago
Timeline
5 articles · newest firstClean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
DAR plants support-persistent backdoors that stay above 96 percent success after clean-data distillation.
58
Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP
CLIPGuard localizes and inpaints CLIP embedding backdoors, cutting attack success to about 1% in black-box tests.
52
Robot Visions: Breaking reCAPTCHA at Zero Cost and Zero Shot
Researchers defeat Google reCAPTCHA using free local models CLIP and OWLv2, achieving 92.6% per-session success at zero cost.
60
GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting
GoDeep achieves annotation-free open-vocabulary 3D segmentation by grounding structured image descriptions in language-only embeddings, outperforming CLIP-based lifting on out-of-vocabulary objects.
26
Appears with
- CLIPai model · 2
- Googlevendor · 2
- Google AI Researchorganization · 1
- Gemini 2.5 Flashai model · 1
- Gemini 2.5 Proai model · 1
- GoDeepproduct · 1
- ScanNet++product · 1
- reCAPTCHAproduct · 1
- OWLv2product · 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.