深度学习 · self supervised learning论文趋势 2023–2026

主要结论

• 深度学习 · self supervised learning论文从 2023 年的 455 篇增长到 2026 年的 534 篇，三年间扩大到约 1.2 倍。
• ICLR 是发深度学习 · self supervised learning论文最多的会议，2023–2026 年共 693 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是通用机器学习 · unsupervised and semisupervised learning：同时属于两个主题的论文从 2023 年的 23 篇增至 2026 年的 86 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 4；同组增长最快的扩散模型是 4.1 倍，深度学习 · self supervised learning是 1.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部深度学习 · self supervised learning论文

共 693 篇，第 3 / 14 页

101. ICLR 2026Measuring the Intrinsic Dimension of Earth Representations
102. ICLR 2026Mechanistic Independence: A Principle for Identifiable Disentangled Representations
103. ICLR 2026MILCO: Learned Sparse Retrieval Across Languages via a Multilingual Connector
104. ICLR 2026Mini-cluster Guided Long-tailed Deep Clustering
105. ICLR 2026Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
106. ICLR 2026Modeling the Density of Pixel-level Self-supervised Embeddings for Unsupervised Pathology Segmentation in Medical CT
107. ICLR 2026Multi-ReduNet: Interpretable Class-Wise Decomposition of ReduNet
108. ICLR 2026Multimodal Classification via Total Correlation Maximization
109. ICLR 2026Multimodal Dataset Distillation via Phased Teacher Models
110. ICLR 2026MULTIMODALITY AS SUPERVISION: SELF-SUPERVISED SPECIALIZATION TO THE TEST ENVIRONMENT VIA MULTIMODALITY
111. ICLR 2026NAB: Neural Adaptive Binning for Sparse-View CT reconstruction
112. ICLR 2026Neural Dynamics Self-Attention for Spiking Transformers
113. ICLR 2026Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers
114. ICLR 2026Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
115. ICLR 2026On the Alignment Between Supervised and Self-Supervised Contrastive Learning
116. ICLR 2026On the Wasserstein Geodesic Principal Component Analysis of probability measures
117. ICLR 2026Once-More: Continuous Self-Correction for Large Language Models via Perplexity-Guided Intervention
118. ICLR 2026One protein is all you need
119. ICLR 2026One-Shot Exemplars for Class Grounding in Self-Supervised Learning
120. ICLR 2026Optimizer Choice Matters For The Emergence of Neural Collapse
121. ICLR 2026OrthoRF: Exploring Orthogonality in Object-Centric Representations
122. ICLR 2026Out-of-Distribution Graph Models Merging
123. ICLR 2026Poly-attention: a general scheme for higher-order self-attention
124. ICLR 2026Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation
125. ICLR 2026Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
126. ICLR 2026Pseudo-Non-Linear Data Augmentation: A Constrained Energy Minimization Viewpoint
127. ICLR 2026PU-BENCH: A UNIFIED BENCHMARK FOR RIGOROUS AND REPRODUCIBLE PU LEARNING
128. ICLR 2026Reconstruct Anything Model a lightweight foundation model for computational imaging
129. ICLR 2026Reducing Class-Wise Performance Disparity via Margin Regularization
130. ICLR 2026RESTRAIN: From Spurious Votes to Signals — Self-Training RL with Self-Penalization
131. ICLR 2026Resurfacing the Instance-only Dependent Label Noise Model through Loss Correction
132. ICLR 2026Rethinking Consistent Multi-Label Classification under Inexact Supervision
133. ICLR 2026Rethinking JEPA: Compute‑Efficient Video Self-Supervised Learning with Frozen Teachers
134. ICLR 2026Riemannian Optimization on Relaxed Indicator Matrix Manifold
135. ICLR 2026RigidSSL: Rigidity-based Geometric Pretraining for Protein Generation
136. ICLR 2026Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
137. ICLR 2026Robustify Spiking Neural Networks via Dominant Singular Deflation under Heterogeneous Training Vulnerability
138. ICLR 2026S$^2$-Guidance: Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
139. ICLR 2026Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
140. ICLR 2026SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback
141. ICLR 2026Samples Are Not Equal: A Sample Selection Approach for Deep Clustering
142. ICLR 2026SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised Learning
143. ICLR 2026SeeDNorm: Self-Rescaled Dynamic Normalization
144. ICLR 2026Selective Rotary Position Embedding
145. ICLR 2026Self-Consistency Improves the Trustworthiness of Self-Interpretable GNNs
146. ICLR 2026Self-Destructive Language Models
147. ICLR 2026Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
148. ICLR 2026Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
149. ICLR 2026Self-Speculative Masked Diffusions
150. ICLR 2026Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · self supervised learning论文？

共 1,958 篇，按年份分别是 2023 年 455 篇、2024 年 472 篇、2025 年 497 篇、2026 年 534 篇。

NeurIPS 2026 有多少篇深度学习 · self supervised learning论文？

NeurIPS 2026 有 110 篇深度学习 · self supervised learning论文，上一届是 147 篇。

ICLR 2026 有多少篇深度学习 · self supervised learning论文？

ICLR 2026 有 195 篇深度学习 · self supervised learning论文，上一届是 195 篇。

ICML 2026 有多少篇深度学习 · self supervised learning论文？

ICML 2026 有 135 篇深度学习 · self supervised learning论文，上一届是 72 篇。

CVPR 2026 有多少篇深度学习 · self supervised learning论文？

CVPR 2026 有 94 篇深度学习 · self supervised learning论文，上一届是 83 篇。

哪个会议的深度学习 · self supervised learning论文最多？

ICLR，2023–2026 年共 693 篇。