AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations

Yilun Kuang, Yash Dagade, Tim G. J. Rudner, Randall Balestriero, Yann LeCun

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
rectify both features and the target distribution (RGN p | z+) instead of other combinations (ablation)Rectified LpJEPA · CIFAR-100 validationaccuracy vs sparsity tradeoffImproved
match rectified features to an isotropic Gaussian target (ablation)Rectified LpJEPA · CIFAR-100 validationaccuracyHurt
do not rectify features or target (LpJEPA) (ablation)Rectified LpJEPA · CIFAR-100 validationsparsityHurt
apply an extra ReLU to LpJEPA features instead of matching the rectified target (ablation)LpJEPA · linear probe evaluationaccuracyHurt
vary mean shift mu and p in the target distribution (ablation)Rectified LpJEPA · pretrained ResNet, ViT, ConvNeXtempirical L0 norm vs theoryImproved
increase sparsity of features up to about 95% zeros (ablation)Rectified LpJEPA · CIFAR-100 validationaccuracyNo clear effect
push sparsity beyond about 95% zeros (mu = -2.5) (ablation)Rectified LpJEPA · ImageNet-100 linear probeAcc1 projector: 80.00 -> 67.82 (RGN 2.0(0) vs RGN 2.0(-2.5))Hurt
use Rectified LpJEPA instead of Gaussian-based LeJEPAJEPA · ImageNet-100 linear probe (encoder)Acc1 (%): 84.80 -> 85.08Improved
use Rectified LpJEPA instead of Non-Negative VICRegsparse JEPA · ImageNet-100 linear probe (projector)Acc1 (%): 77.74 -> 80.40Improved
use Rectified LpJEPA instead of VICReg or NVICRegJEPA · pairwise independencenormalized HSICImproved
use eigenvectors of feature covariance as projection vectors (ablation)RDMReg · convergence speedconvergence to optimal performanceImproved
raise mean shift to reduce sparsity, trading sparsity for entropy (ablation)Rectified LpJEPA · d(xi)-dimensional entropyentropyMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy