Contrastive & Self-Supervised Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Self-supervision turns unlabeled data into its own teacher. This list covers contrastive fundamentals — augmentations, negatives, and momentum — through redundancy reduction and masked modeling, emphasizing what actually transfers to downstream tasks.

Contrastive & Self-Supervised Learning: 10 key papers

1. A Simple Framework for Contrastive Learning of Visual Representations
   Chen et al. arXiv 2020.
2. Momentum Contrast for Unsupervised Visual Representation Learning
   He et al. arXiv 2019.
3. Bootstrap your own latent: A new approach to self-supervised Learning
   Grill et al. arXiv 2020.
4. Improved Baselines with Momentum Contrastive Learning
   Chen et al. arXiv 2020.
5. Exploring Simple Siamese Representation Learning
   Chen and He. arXiv 2020.
6. Masked Autoencoders Are Scalable Vision Learners
   He et al. arXiv 2021.
7. Emerging Properties in Self-Supervised Vision Transformers
   Caron et al. arXiv 2021.
8. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
   Caron et al. arXiv 2020.
9. Barlow Twins: Self-Supervised Learning via Redundancy Reduction
   Zbontar et al. arXiv 2021.
10. Representation Learning with Contrastive Predictive Coding
    van den Oord et al. arXiv 2018.

Related reading lists

• Representation Learning for RL
• Data Augmentation for Reinforcement Learning
• Goal-Conditioned Reinforcement Learning
• Vision-Language Models & Multimodal Learning
• Bayesian Deep Learning
• Block MDPs & Latent State Discovery
• Mechanistic Interpretability
• Anomaly & Out-of-Distribution Detection