Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion

• URL: http://arxiv.org/abs/2605.24631v1
• Date: Sat, 23 May 2026 15:40:56 GMT
• Title: Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
• Abstract summary: We propose a world-centric perspective on minority sampling, which defines rarity with respect to real-world priors.<n>We introduce JEPA guidance, a diffusion sampling framework guided by a Joint-Embedding Predictive Architecture.<n>We show that JEPA guidance consistently improves the fidelity and semantic validity of minority samples.
• Score: 7.276372008305617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Minority sampling aims to generate low-density instances on a data manifold and is of central importance in applications such as medical diagnosis, anomaly detection, and creative AI. Existing approaches, however, define minority samples relative to generative priors learned from training data, confining rarity to model-specific notions that may poorly reflect real-world semantics. In this work, we propose a world-centric perspective on minority sampling, which defines rarity with respect to real-world priors rather than generator-induced densities. To this end, we introduce JEPA guidance, a diffusion sampling framework guided by a Joint-Embedding Predictive Architecture (JEPA) -- a class of world models that encode broad, semantically rich representations. JEPA guidance steers diffusion trajectories toward low-density regions under the implicit density induced by the JEPA, thereby aligning generated minorities with real-world semantic rarity. To make JEPA guidance computationally practical, we develop principled approximation strategies accompanied by theoretical error bounds, significantly reducing the overhead of guidance computation. Extensive experiments across unconditional, class-conditional, and text-to-image generation demonstrate that JEPA guidance consistently improves the fidelity and semantic validity of minority samples, outperforming generator-centric baselines in capturing real-world notions of rarity. Code is available at https://github.com/soobin-um/jepa-guidance.

Related papers

• A Generalization Theory for JEPA-Based World Models [34.09833992943572]
  Joint Embedding Predictive Architectures (JEPAs) have emerged as a promising paradigm for world modeling.<n>Despite their empirical success, the theoretical understanding of JEPA-based world models remains limited.
  arXiv  Detail & Related papers  (2026-06-25T13:29:20Z)
• Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models [26.928611870426383]
  JointEmbedding Predictive Architectures (JEPAs) provide a simple framework for learning world models by predicting future latent representations.<n>The recent LeWorldModel (LeWM) shows that this issue can be alleviated bysimply constraining latent embeddings with an isotropic Gaussian prior.<n>We propose ame, which seeks a favorable operatingpoint on the bias-variance frontier by applying Gaussian constraints inmultiple random subspaces rather than in the originalembedding space.
  arXiv  Detail & Related papers  (2026-05-10T00:51:47Z)
• ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model [53.15040805435013]
  Vision-language models (VLMs) provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames.<n>We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance.
  arXiv  Detail & Related papers  (2026-03-23T17:59:42Z)
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics [53.247652209132376]
  Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D.<n>We present a comprehensive theory of JEPAs and instantiate it in bf LeJEPA, a lean, scalable, and theoretically grounded training objective.
  arXiv  Detail & Related papers  (2025-11-11T18:21:55Z)
• Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density [51.15085346971361]
  Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box.<n>JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of a slightly perturbed sample must be predictable from the original sample's representation, and (ii) an anti-collapse term, i.e., not all samples should have the same representation.
  arXiv  Detail & Related papers  (2025-10-07T14:06:30Z)
• Learning Majority-to-Minority Transformations with MMD and Triplet Loss for Imbalanced Classification [0.5390869741300152]
  Class imbalance in supervised classification often degrades model performance by biasing predictions toward the majority class.<n>We introduce an oversampling framework that learns a parametric transformation to map majority samples into the minority distribution.<n>Our approach minimizes the mean maximum discrepancy (MMD) between transformed and true minority samples for global alignment.
  arXiv  Detail & Related papers  (2025-09-15T01:47:29Z)
• Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation [57.19995625893062]
  Minority samples are underrepresented instances located in low-density regions of a data manifold.<n>We present a simple yet powerful guidance-free approach called Boost-and-Skip for generating minority samples.<n>We highlight that these seemingly-trivial modifications are supported by solid theoretical and empirical evidence.
  arXiv  Detail & Related papers  (2025-02-10T14:37:26Z)
• Denoising with a Joint-Embedding Predictive Architecture [21.42513407755273]
  We introduce Denoising with a Joint-Embedding Predictive Architecture (D-JEPA)<n>By recognizing JEPA as a form of masked image modeling, we reinterpret it as a generalized next-token prediction strategy.<n>We also incorporate diffusion loss to model the per-token probability distribution, enabling data generation in a continuous space.
  arXiv  Detail & Related papers  (2024-10-02T05:57:10Z)
• Self-Guided Generation of Minority Samples Using Diffusion Models [57.319845580050924]
  We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the principle of guided sampling. Experiments on benchmark real datasets demonstrate that our approach can greatly improve the capability of creating realistic low-likelihood minority instances.
  arXiv  Detail & Related papers  (2024-07-16T10:03:29Z)
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data [125.7135706352493]
  Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator.
  arXiv  Detail & Related papers  (2021-11-12T18:13:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.