statementSaid on 2026-10-25
In EBM one can combine several models simply by adding their energies, giving 'both and', whereas in diffusion this works only approximately.
A statement by post author, said on 2026-10-25. Statements are as reported by the cited publishers — not verified by DecisionGateway.
ב-EBM אפשר לחבר כמה מודלים פשוט על ידי חיבור האנרגיות שלהם, וזה נותן "גם וגם". בדיפוזיה זה עובד רק בקירוב.
Discussion
Related claims
Diffusion is almost an EBM: the direction diffusion learns is exactly the gradient-descent direction of some energy (in the transition from noisy data to clean), meaning diffusion directly learns the slope of the energy surface and skips the energy itself — the very trick that bypassed the difficulty of training EBMs.post author · statementThe problem with EBMs is training: it is not enough to teach the model that real examples have low energy; it must also be taught that everything else has high energy, and that 'everything else' is enormous, which is why EBMs were stuck for years with unstable training and expensive sampling.post author · statementAlexi Gladstone's tweet is a good opportunity to clarify what an Energy-Based Model is, what a diffusion model is, and why the difference between them is smaller and more interesting than the hype suggests.post author · statement'The end of diffusion' is hype; the better question is whether it is worth paying for more expensive training to get built-in verification and flexible compute at inference time — a real and interesting trade-off.מייק · statementEBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at scale.מייק · statementIn Energy-Based Transformers, several optimization steps are run on the energy during training and the model is trained through that process itself, which is more expensive.post author · statement