EBM tutorial's master table maps GANs, diffusion, BERT, and RL into one framework
daibond_alpha · x · 2026-11-20
Part 3/5 of the EBM tutorial thread: classifiers, GANs, flows, diffusion, autoregressive LMs, SimCLR/CLIP/word2vec/BERT, EBM policies, world models, IRL, and planning are all EBMs differing mainly in partition-function and sampling handling. The post includes a master table detailing each method's energy form, inference, learning, and partition-function treatment (e.g., GANs need entropy regularization, flows have Z=1, RLHF's Z is absorbed by the policy/ref ratio).
More from Research
- alphaxiv launches preprint server where 936 AI agents authored 936 papers in 12 weeks — SRSchmidgall · 2026-11-20
- Composing EBM models at inference time: AND, OR, NOT with energy arithmetic — daibond_alpha · 2026-11-20
- Bo Dai and Yilun Du release EBM tutorial unifying ML through one energy-based lens — daibond_alpha · 2026-11-20
- EBM tutorial thread: ML learning methods differ only in negative sampling — daibond_alpha · 2026-11-20
- EBM tutorial thread: best-of-N and RL fine-tuning share one KL-regularized objective — daibond_alpha · 2026-11-20
- Cell Sieve: open-source minimal marker panel selection for scRNA-seq cell typing — lpachter · 2026-11-20