# Next-Embedding Prediction Makes Strong Vision Learners

arXiv: https://arxiv.org/abs/2512.16922 · HTML: https://mlsanity.com/paper/2512.16922/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 76 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 30 of 57)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)

## Built on by (most cited first, 23 of 23)

- [Beyond Language Modeling: An Exploration of Multimodal Pretraining](https://mlsanity.com/paper/2603.03276/) (2026)
- [Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching](https://mlsanity.com/paper/2602.05951/) (2026)
- [ViT-5: Vision Transformers for The Mid-2020s](https://mlsanity.com/paper/2602.08071/) (2026)
- [LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning](https://mlsanity.com/paper/2607.00958/) (2026)
- [Next Embedding Prediction Makes World Models Stronger](https://mlsanity.com/paper/2603.02765/) (2026)
- [Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction](https://mlsanity.com/paper/2603.16281/) (2026)
- [Self-Supervised Learning as Discrete Communication](https://mlsanity.com/paper/2602.09764/) (2026)
- [EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models](https://mlsanity.com/paper/2602.14024/) (2026)
- [Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework](https://mlsanity.com/paper/2605.17566/) (2026)
- [Vision Harnessing Agent for Open Ad-hoc Segmentation](https://mlsanity.com/paper/2605.19410/) (2026)
- [Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs](https://mlsanity.com/paper/2607.18412/) (2026)
- [Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction](https://mlsanity.com/paper/2608.12209/) (2026)
- [Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning](https://mlsanity.com/paper/2608.15869/) (2026)
- [PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation](https://mlsanity.com/paper/2609.38597/) (2026)
- [Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition](https://mlsanity.com/paper/2603.13904/) (2026)
- [PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL](https://mlsanity.com/paper/2605.02917/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners](https://mlsanity.com/paper/2608.19863/) (2026)
- [Conditional Predictive Sufficient Statistics for Visual Representation Learning](https://mlsanity.com/paper/2609.30647/) (2026)
- [Generative Residual Factorization](https://mlsanity.com/paper/2609.34824/) (2026)
- [One-Step Next-Latent Prediction Is Not a World Model](https://mlsanity.com/paper/2609.36227/) (2026)
- [Embedding Prediction Helps Image Generation](https://mlsanity.com/paper/2610.02203/) (2026)
- [Least Squares for Time Series Forecasting](https://mlsanity.com/paper/2610.03812/) (2026)

## Abstract (arXiv)

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to generate embeddings to perform predictive tasks directly. This work explores such a shift from learning representations to learning models. Specifically, models learn to predict future patch embeddings conditioned on past ones, using causal masking and stop gradient, which we refer to as Next-Embedding Predictive Autoregression (NEPA). We demonstrate that a simple Transformer pretrained on ImageNet-1k with next embedding prediction as its sole learning objective is effective - no pixel reconstruction, discrete tokens, contrastive loss, or task-specific heads. This formulation retains architectural simplicity and scalability, without requiring additional design complexity. NEPA achieves strong results across tasks, attaining 83.8% and 85.3% top-1 accuracy on ImageNet-1K with ViT-B and ViT-L backbones after fine-tuning, and transferring effectively to semantic segmentation on ADE20K. We believe generative pretraining from embeddings provides a simple, scalable, and potentially modality-agnostic alternative to visual self-supervised learning.