Direct Preference Optimization, every mention
4 scenes across 2 shows · ← back to Direct Preference Optimization
tap a year for its mentions
Latent Space 4
the MAD Podcast 3
every year every show Latent Space 4 the MAD Podcast 3
Verbatim, from the transcripts: passages where Direct Preference Optimization comes up on Latent Space, the MAD Podcast
[State of AI Papers 2025] Fixing Research with Social Signals, OCR & Implementation — Team AlphaXiv
- ▶ 3:45 unnamed speaker I think when we started, we were very deliberate about getting authors, like, from LoRa, DPO, Lama, and actually having really useful, cool exchanges.
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
[Paper Club] Intro to Diffusion Models and OpenAI sCM: Simple, Stable, Scalable Consistency Models
- ▶ 49:35 unnamed speaker I think the other one was probably PPO or DPO.
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
- ▶ 1:07:40 Soumith Chintala Um, yeah, and I think DPO also came out of like, ah, like, um, the academic open source side of things. 2 times in the scene