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 2 / 14 页

51. ICLR 2026Diverse Dictionary Learning
52. ICLR 2026Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models
53. ICLR 2026Dual Perspectives on Non-Contrastive Self-Supervised Learning
54. ICLR 2026Dual-Path Condition Alignment for Diffusion Transformers
55. ICLR 2026DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
56. ICLR 2026Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
57. ICLR 2026ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
58. ICLR 2026Equivariant Splitting: Self-supervised learning from incomplete data
59. ICLR 2026Escaping the Homophily Trap: A Threshold-free Graph Outlier Detection Framework via Clustering-guided Edge Reweighting
60. ICLR 2026FedOpenMatch: Towards Semi-Supervised Federated Learning in Open-Set Environments
61. ICLR 2026Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning
62. ICLR 2026Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection
63. ICLR 2026Forest-Based Graph Learning for Semi-Supervised Node Classification
64. ICLR 2026Gauge-invariant representation holonomy
65. ICLR 2026Generalization Below the Edge of Stability: The Role of Data Geometry
66. ICLR 2026Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
67. ICLR 2026GmNet: Revisiting Gating Mechanisms From A Frequency View
68. ICLR 2026Guiding Mixture-of-Experts with Temporal Multimodal Interactions
69. ICLR 2026H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Self-Supervised Node Encoding
70. ICLR 2026Hierarchical Prototype Learning for Semantic Segmentation
71. ICLR 2026Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
72. ICLR 2026Identifiability and recoverability in self-supervised models
73. ICLR 2026Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation
74. ICLR 2026Improving Set Function Approximation with Quasi-Arithmetic Neural Networks
75. ICLR 2026In Context Semi-Supervised Learning
76. ICLR 2026Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation
77. ICLR 2026Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
78. ICLR 2026Jacobian Aligned Random Forests
79. ICLR 2026JULI: Jailbreak Large Language Models by Self-Introspection
80. ICLR 2026KDP: Simplifying Representation Dynamics in Kernel Space
81. ICLR 2026KLAS: Using Similarity to Stitch Neural Networks for an Improved Accuracy-Efficiency Tradeoff
82. ICLR 2026Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
83. ICLR 2026LANE: Label-Aware Noise Elimination for Fine-Grained Text Classification
84. ICLR 2026Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation
85. ICLR 2026LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
86. ICLR 2026Latent Diffusion Model without Variational Autoencoder
87. ICLR 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
88. ICLR 2026LayerSync: Self-aligning Intermediate Layers
89. ICLR 2026Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
90. ICLR 2026Learning Explicit Single-Cell Dynamics Using ODE Representations
91. ICLR 2026Learning from Label Proportions via Proportional Value Classification
92. ICLR 2026Learning Robust Intervention Representations with Delta Embeddings
93. ICLR 2026Learning Unified Representation of 3D Gaussian Splatting
94. ICLR 2026Let OOD Feature Exploring Vast Predefined Classifiers
95. ICLR 2026LLM DNA: Tracing Model Evolution via Functional Representations
96. ICLR 2026LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
97. ICLR 2026Lossy Common Information in a Learnable Gray-Wyner Network
98. ICLR 2026MAPSS: Manifold-based Assessment of Perceptual Source Separation
99. ICLR 2026Maximizing Asynchronicity in Event-based Neural Networks
100. ICLR 2026Maximizing Incremental Information Entropy for Contrastive Learning

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。