Correction term is key to counterfactual reasoning in JEPA world models
randall_balestr · x · 2026-11-20
Follow-up on the JEPA counterfactual world model work: neither the JEPA predictor alone nor a stochastic predictor suffices. The method defines the counterfactual estimate as z{t+1} + μ(Ht,a') − μ(Ht,at) — a simple but necessary correction term — and for nonlinear readouts, guarantees additionally require controlling error in the decoded action contrast.
Related event: LeCun and Colleagues Release Counterfactual World Models Paper(12 posts)→
More from Research
- Lean community certifies Riemann proof; honeypot fake keys expose breaches at three AI providers — LeviTurk · 2026-11-22
- Riemann hypothesis 'proven by Turkish mathematician using AI' claim mocked as the 'Organic Turk' — CatAstro_Piyush · 2026-11-22
- Andriy Burkov releases The Hundred-Page Language Models Book, hands-on with PyTorch — burkov · 2026-11-22
- Generative AI meets cardiology: Dagstuhl seminar bridges ML and clinical practice — StephanMandt · 2026-11-22
- SubRoformer hits SOTA music source separation with DSP subband filters — affige_yang · 2026-11-22
- Emily Riehl releases Lean game teaching dependent type theory at intro-to-proofs level — abhi9u · 2026-11-22