Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
arXiv·Andy Zeyi Liu·Sep 9, 2026, 5:08 PM

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization

Papers78

Evaluating world models under qualitative physical shifts, SG-JEPA extends the JEPA framework to achieve zero-shot generalization across varying gravitational regimes. By conditioning on physics-governing parameters and back-propagating autoregressive rollout loss into the encoder, the method cuts 2D open-loop prediction error by half and improves 3D robotic manipulation success by up to 2.5 times over DINO-WM. Theoretical analysis indicates that performance gains stem primarily from the encoder retaining rollout-consistent representations rather than the predictor merely fitting dynamic trajectories.

Why it's worth reading

It addresses physical out-of-distribution generalization in JEPA world models, showing analytically and empirically that back-propagating rollout loss forces the representation encoder to retain dynamically consistent features.

Tags

JEPAworld-modelsroboticsphysics-generalizationreinforcement-learningrepresentation-learning

Score breakdown

  • Novelty82
  • Impact76
  • Practicality74
  • Credibility80
  • Timeliness78