Deep learning · self supervised learning papers, 2023–2026

Key findings

• Deep learning · self supervised learning went from 455 papers in 2023 to 534 in 2026, roughly 1.2x in three years.
• ICLR publishes the most Deep learning · self supervised learning work: 693 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with General ML · unsupervised and semisupervised learning: papers tagged with both rose from 23 in 2023 to 86 in 2026.
• Among the 11 topics under Deep Learning, it ranks #4 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
• ICML 20263D-DLP: Self-supervised 3D Object-centric Scene Representation Learning
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026A Stitch in Time Learning Procedural Workflow via Self-Supervised Plackett-Luce
• NeurIPS 2025$\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
• ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
• ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
• CVPR 2025A Unified Framework for Heterogeneous Semi-supervised Learning
• NeurIPS 2024Intrinsic Self-Supervision for Data Quality Audits
• ICML 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
• ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• CVPR 2024Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios
• NeurIPS 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
• ICML 2023A Closer Look at Self-Supervised Lightweight Vision Transformers
• ICLR 2023A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
• CVPR 2023Are Data-Driven Explanations Robust Against Out-of-Distribution Data?
• NeurIPS 2026AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
• ICML 20263DPoV: Improving 3D understanding via Patch Ordering on Videos
• ICLR 2026Angle K-Means
• CVPR 2026Action Motifs Self-Supervised Hierarchical Representation of Human Body Movements

All Deep learning · self supervised learning papers

426 papers, page 3 of 9

101. CVPR 2025AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning
102. CVPR 2025BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment
103. CVPR 2025Boost the Inference with Co-training: A Depth-guided Mutual Learning Framework for Semi-supervised Medical Polyp Segmentation
104. CVPR 2025CGMatch: A Different Perspective of Semi-supervised Learning
105. CVPR 2025CLIP-driven Coarse-to-fine Semantic Guidance for Fine-grained Open-set Semi-supervised Learning
106. CVPR 2025Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space
107. CVPR 2025Consistency-aware Self-Training for Iterative-based Stereo Matching
108. CVPR 2025COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
109. CVPR 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
110. CVPR 2025DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension
111. CVPR 2025FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
112. CVPR 2025FFR: Frequency Feature Rectification for Weakly Supervised Semantic Segmentation
113. CVPR 2025Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions
114. CVPR 2025FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning
115. CVPR 2025GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
116. CVPR 2025Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
117. CVPR 2025Generating 3D-Consistent Videos from Unposed Internet Photos
118. CVPR 2025GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation
119. CVPR 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
120. CVPR 2025Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks
121. CVPR 2025Invisible Backdoor Attack against Self-supervised Learning
122. CVPR 2025Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
123. CVPR 2025Learning Class Prototypes for Unified Sparse-Supervised 3D Object Detection
124. CVPR 2025Learning Dynamic Collaborative Network for Semi-supervised 3D Vessel Segmentation
125. CVPR 2025Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes
126. CVPR 2025Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model
127. CVPR 2025Learning Textual Prompts for Open-World Semi-Supervised Learning
128. CVPR 2025Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition
129. CVPR 2025Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
130. CVPR 2025Masking meets Supervision: A Strong Learning Alliance
131. CVPR 2025Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch
132. CVPR 2025Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation
133. CVPR 2025Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds
134. CVPR 2025MVDoppler-Pose: Multi-Modal Multi-View mmWave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation
135. CVPR 2025Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
136. CVPR 2025ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry Staining
137. CVPR 2025On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Events
138. CVPR 2025ONDA-Pose: Occlusion-Aware Neural Domain Adaptation for Self-Supervised 6D Object Pose Estimation
139. CVPR 2025Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
140. CVPR 2025Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances
141. CVPR 2025PointSR: Self-Regularized Point Supervision for Drone-View Object Detection
142. CVPR 2025Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising
143. CVPR 2025POT: Prototypical Optimal Transport for Weakly Supervised Semantic Segmentation
144. CVPR 2025Probing the Mid-level Vision Capabilities of Self-Supervised Learning
145. CVPR 2025PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds
146. CVPR 2025Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers
147. CVPR 2025Rotation-Equivariant Self-Supervised Method in Image Denoising
148. CVPR 2025S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Model with Spatio-Temporal Visual Representation
149. CVPR 2025Sea-ing in Low-light
150. CVPR 2025Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning

FAQ

How many Deep learning · self supervised learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,958 in total: 455 in 2023, 472 in 2024, 497 in 2025, 534 in 2026.

How many Deep learning · self supervised learning papers are at NeurIPS 2026?

NeurIPS 2026 has 110 Deep learning · self supervised learning papers, versus 147 the year before.

How many Deep learning · self supervised learning papers are at ICLR 2026?

ICLR 2026 has 195 Deep learning · self supervised learning papers, versus 195 the year before.

How many Deep learning · self supervised learning papers are at ICML 2026?

ICML 2026 has 135 Deep learning · self supervised learning papers, versus 72 the year before.

How many Deep learning · self supervised learning papers are at CVPR 2026?

CVPR 2026 has 94 Deep learning · self supervised learning papers, versus 83 the year before.

Which conference publishes the most Deep learning · self supervised learning papers?

ICLR, with 693 papers from 2023 to 2026.