On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “LeJEPA”

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscs.LG

LeJEPA provides a scalable, theory-driven approach to self-supervised learning.

problem Lack of practical guidance and theory in JEPAs.

method Identified optimal Gaussian distribution and introduced SIGReg objective.

result LeJEPA achieves state-of-the-art performance with minimal hyperparameters and heuristics.

self-supervised learning predictive architectures Gaussian distribution scalable training theory-driven approach

2025-11-11abs ↗pdf ↗

When Does LeJEPA Learn a World Model?stat.ML

LeJEPA learns latent variables from nonlinear observations.

problem Learning latent variables from nonlinear observations.

method Proves linear identifiability of Gaussian latent distributions.

result Gaussian distribution uniquely guarantees linear identifiability.

World Models Latent Variables Linear Identifiability Gaussian Distribution LeJEPA

2026-05-25abs ↗pdf ↗