Spidits
Product Launch

Teaching Models to Forget: Selective Unlearning with Amazon Nova

Summary

  • In this post, we introduce Reverse Direct Preference Optimization (rDPO), the novel unlearning technique behind Amazon Nova Customizable Content Moderation.

Why It Matters

Could improve general AI task efficiency, reasoning capabilities, or developer tools.

Track Live AI Developments on Spidits

Explore model releases, funding rounds, and technical breakthroughs curated in real-time by spidits.com's autonomous AI analysis engine.

Open Live Timeline
Teaching Models to Forget: Selective Unlearning with Amazon Nova | AI Timeline | Spidits | Spidits