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 135 篇，第 3 / 3 页

101. ICML 2026Self-Supervised Dynamical System Representations for Physiological Time-Series
102. ICML 2026Self-supervised Hierarchical Visual Reasoning with World Model
103. ICML 2026Self-Supervised Learning as Discrete Communication
104. ICML 2026Self-Supervised Weight Templates for Scalable Vision Model Initialization
105. ICML 2026SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
106. ICML 2026Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
107. ICML 2026Semi-Supervised Hypothesis Testing by Betting on Predictions
108. ICML 2026Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations
109. ICML 2026SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
110. ICML 2026SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
111. ICML 2026SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
112. ICML 2026SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
113. ICML 2026Spectral Guidance for Flexible and Efficient Control of Diffusion Models
114. ICML 2026SpikeCLR: Self-Supervised Contrastive Learning for Visual Representations with Spiking Neural Networks
115. ICML 2026Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
116. ICML 2026SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
117. ICML 2026STAND: Self-Aware Precondition Induction for Interactive Task Learning
118. ICML 2026Structure Enables Effective Self-Localization of Errors in LLMs
119. ICML 2026Supervised Graph Contrastive Learning for Gene Regulatory Networks
120. ICML 2026SURF: Separation via Unsupervised Remixing Flow
121. ICML 2026TabularBERT: Binning-Based Self-Supervised Learning for Tabular Representation
122. ICML 2026The Extra Tokens Matter: Disentangled Representation Learning with Vision Transformers
123. ICML 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
124. ICML 2026The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
125. ICML 2026The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
126. ICML 2026TMS: Trajectory-Mixed Supervision for On-Policy Self Distillation
127. ICML 2026Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
128. ICML 2026TriForces: Augmenting Atomistic GNNs for Transferable Representations
129. ICML 2026Understanding Self-Supervised Learning via Latent Distribution Matching
130. ICML 2026USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning
131. ICML 2026Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture – Bridging Predictive and Generative Self-Supervised Learning
132. ICML 2026Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention
133. ICML 2026VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
134. ICML 2026Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
135. ICML 2026When Softmax Fails at the Top: Extreme‑Value Corrections for InfoNCE

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。