Subgraph Atlas · centered on entity
Identity Preference Optimization (IPO)
technique0 mentions· velocity: stableA preference-optimization variant that avoids DPO's over-fitting by adding an explicit regularizer.
Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.
0 nodes · 0 edges · loading…
companypersonai_modelproductresearch_labbenchmarkframework
drag to move · scroll to zoom · click a node
Top connections
Googlecompany
356 mentions
→ Center atlas here
Reinforcement Learning from Human Feedback (RLHF)technique
4 mentions
→ Center atlas here
A General Theoretical Paradigm to Understand Learning from Human Preferencespaper
0 mentions
→ Center atlas here
Direct Preference Optimization (DPO)technique
0 mentions
→ Center atlas here