causal masking
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Aug 4, 2025 by Stefano Ermon · across every show →
Everything said about causal masking, oldest first
Aug 4, 2025 neutral
Ermon: Adapting Pretrained Causal LLMs to Diffusion Models Is Difficult
“The challenge is that, yeah, the training objective is quite different because you are training based on denoising as opposed to next token prediction. Diffusion models are not causal and that is also kind of problematic. I mean, it's a big advantage of diffus…”