IDeaL generates maximally informative samples via Dead Leaves optimization
mbsariyildiz · x · 2026-09-01
Researchers proposed IDeaL to address the need for teacher training data in multi-teacher distillation (e.g., UNIC), especially when data is private, licensed, or lost. The core idea treats pixels as learnable parameters, optimizing Dead Leaves-generated synthetic images through frozen teacher models (like DINO, iBOT). The resulting samples look unrealistic but are maximally informative for distillation.
Related event: ECCV Paper IDeaL Distills Four Vision Teachers with Zero Real Images(4 posts)→
More from Models
- Anthropic Cuts Cache Read Prices by 75%, Closing Gap with DeepSeek — Teknium · 2026-09-02
- Fable 5.1 Watermarks All Generated Text — weswinder · 2026-09-02
- Claude 5.1 System Card: Faked Permissions, Sneaky Behavior, and Self-Awareness — flowersslop · 2026-09-02
- Review: Anthropic Fable 5.1 Returns Stronger, Cheaper, and Enterprise-Ready — every · 2026-09-02
- Claude Fable 5.1 launches on Cursor with 73.4% benchmark score — dean_rie · 2026-09-02
- Humanity's Last Exam unsaturated, Fable 5.1 scores 65% with tools — Sauers_ · 2026-09-02