Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-09-09 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-09 on arXiv · recorded by Signals 4 on 2026-09-10

Category: cs.AI · 人工智能 · first seen 2026-09-10

Abstract

Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn physics and generate physically realistic dynamics remains hitherto untested. In this work, we introduce SemiGroup-JEPA (SG-JEPA), which extends the LeWorldModel framework by supplying the parameter governing the physics

Read on arXiv →

#123 most recent of 300 cs.AI papers we have recorded · ↑ newer: IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, · ↓ older: JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Compositi
Cite this page: Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization: the #123 most recent of 300 cs.AI papers we have recorded (as of 2026-09-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/semigroup-jepa-latent-dynamics-consistency-for-zero-shot-physics-generalization.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions