Direct Preference Optimization, every mention
1 scene (said by Douwe Kiela) · ← back to Direct Preference Optimization
tap a year for its mentions
every year anyone Douwe Kiela 3
Verbatim, from the transcripts: the passages where Direct Preference Optimization comes up
Top AI Researcher on GPT 4.5, DeepSeek and Agentic RAG | Douwe Kiela, CEO, Contextual AI
- ▶ 38:12 Douwe Kiela Yeah, so, so, um, uh, KTO, um, is a different way, uh, to do, uh, DPO, so direct preference optimization. 3 times in the scene