清华大学李升波团队：将JEPA与受控世界模型结合，揭示物理状态与动作转移的可辨识条件
Ranking
Overall
62
Content
75
Popularity
33
Observed public metrics from 1 member.
Merged summary
TL;DR - Tsinghua's iDLab (Shengbo Eben Li) with DiDi's Voyager Lab extends LeCun's JEPA identifiability theory from autonomous to controlled world models, proving when a latent encoder can recover both true physical states and the action-driven transition dynamics (arXiv:2607.22430).
- Introduces two policy-dependent metrics: representation margin (spectral gap between weakest first-order latent predictive signal and strongest higher-order nonlinear surrogate) and transition margin (weakest residual conditional action variation given state). Identifiability requires both to be strictly positive.
- Theorem 1: under joint-Gaussian behavior data, stationary linear-Gaussian controlled transitions, invertible observation map, and a standard-Gaussian representation constraint, JEPA training recovers true state and transition up to an orthogonal matrix Q; proof expands the encoder into Hermite components so a positive spectral gap forces only first-order terms to survive.
- Theorem 2 gives finite-error bounds splitting error into encoder vs. predictor sources; Theorem 3 shows counterfactual prediction error can be amplified to ~ε/transition-margin — a constructible worst case, not a universal upper bound.
- Experiments on four nonlinear observation maps (spiral, parabolic, sinusoidal, wave) confirm errors fall as margins grow; with zero action coverage, in-distribution error stays low while counterfactual error and A/B matrix estimation degrade, hurting goal-conditioned planning. Practical takeaway: don't judge world models by one-step in-distribution error alone; add exploration noise for offline data collection.
Sources (1)
清华大学李升波团队：将JEPA与受控世界模型结合，揭示物理状态与动作转移的可辨识条件
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - Tsinghua's iDLab (Shengbo Eben Li) with DiDi's Voyager Lab extends LeCun's JEPA identifiability theory from autonomous to controlled world models, proving when a latent encoder can recover both true physical states and the action-driven transition dynamics (arXiv:2607.22430).
- Introduces two policy-dependent metrics: representation margin (spectral gap between weakest first-order latent predictive signal and strongest higher-order nonlinear surrogate) and transition margin (weakest residual conditional action variation given state). Identifiability requires both to be strictly positive.
- Theorem 1: under joint-Gaussian behavior data, stationary linear-Gaussian controlled transitions, invertible observation map, and a standard-Gaussian representation constraint, JEPA training recovers true state and transition up to an orthogonal matrix Q; proof expands the encoder into Hermite components so a positive spectral gap forces only first-order terms to survive.
- Theorem 2 gives finite-error bounds splitting error into encoder vs. predictor sources; Theorem 3 shows counterfactual prediction error can be amplified to ~ε/transition-margin — a constructible worst case, not a universal upper bound.
- Experiments on four nonlinear observation maps (spiral, parabolic, sinusoidal, wave) confirm errors fall as margins grow; with zero action coverage, in-distribution error stays low while counterfactual error and A/B matrix estimation degrade, hurting goal-conditioned planning. Practical takeaway: don't judge world models by one-step in-distribution error alone; add exploration noise for offline data collection.