TEM: Transformer Energy-Based Models claimed to outscale diffusion
MarvinTBaumann · x · 2026-10-30
A thread introduces TEM (Transformer Energy-based Models), billed as the first scalable contrastive EBM—claiming better scaling than diffusion without guidance, plus stronger generalization, test-time scaling and OOD detection. Reposter quips "EBMs are so back (never left)."
Related event: TEM: energy-based models scale for the first time, beating diffusion(3 posts)→
More from Research
- LeRoPE makes RoPE frequencies learnable, beating RoPE across 52M-2.5B scales — eliebakouch · 2026-10-30
- Redwood's Screwtape: 35 monitor-evading attacks from 252 runs on real agent transcripts — dl_weekly · 2026-10-30
- DCOCO paper: contextual correction makes parallel speculative decoding up to 6.6x faster — burny_tech · 2026-10-30
- Datology AI builds synthetic pretraining data with controllable knowledge cutoff guarantees — josh_wills · 2026-10-30
- Grafting task vectors enables constitutional model training for under $500 — burny_tech · 2026-10-30
- Santa Fe Institute publishes interactive history of agent-based modeling, from Game of Life to pandemics — S_Conradi · 2026-10-30