Yilun Du and Dai Bo release EBM tutorial unifying diffusion, RL, and test-time reasoning
burny_tech · x · 2026-11-20
Yilun Du and Dai Bo have released a tutorial, "An Energy-Based Perspective on Machine Learning", arguing that energy-based models shouldn't be taught as just one model family among many, but as a single lens on ML.
Core claim: diffusion models, representation learning, reinforcement learning, and test-time reasoning can each be seen as learning an energy function — or using one to guide sampling and search. The 5-part tutorial series is now available online.
More from Research
- MiniMind: train a 64M-param LLM from scratch in 2 hours on one RTX 3090 — dr_cintas · 2026-11-20
- 1,900 AI-for-science papers in a week: why a small test error proves almost nothing — bravo_abad · 2026-11-20
- The Future of Mech Interp: Abstracting Learned Algorithms From Circuits — burny_tech · 2026-11-20
- MBZUAI's PAN 2 World Model: 29B Params, Fully Open with Weights, Inference and Training Code — ZhitingHu · 2026-11-20
- LLMs show transferable goal encodings: a Python plan replanted into C++ gets re-implemented — paul_cal · 2026-11-20
- Solo researcher maps Qwen3.5-0.8B's 360 components as an ecosystem and repairs damaged models — suayptalha · 2026-11-20