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 2 / 3 页

51. ICML 2026Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
52. ICML 2026Joint-Embedding Predictive Learning of Latent Market States in U.S. Equities
53. ICML 2026KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation
54. ICML 2026KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
55. ICML 2026Language Model Augmented Semi-Supervised Statistical Inference
56. ICML 2026Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
57. ICML 2026Learning Cardiac Latent Representations in Vectorcardiogram Space
58. ICML 2026Learning Randomized Reductions
59. ICML 2026Learning Sparse Visual Representations via Spatial-Semantic Factorization
60. ICML 2026Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
61. ICML 2026Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation
62. ICML 2026Learning to Self-Verify Makes Language Models Better Reasoners
63. ICML 2026Leveraging Lineage Barcodes as Natural Augmentations for Contrastive Learning of Cell Fate in scRNA-seq Data
64. ICML 2026Maximum-Likelihood Learning of Latent Dynamics Without Reconstruction
65. ICML 2026MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation
66. ICML 2026MOES-Pred: Molecular Structural Representation Learning by Adaptive Energy-Sentinel Vibration for Generalized Property Prediction
67. ICML 2026Multi-Label Learning with Contrastive Cluster Self-Supervision for 3D Hierarchical Semantic Segmentation
68. ICML 2026Multiview Self-Representation Learning across Heterogeneous Views
69. ICML 2026Negative Sampling From the Ground Up: A Redesign for Recommendation
70. ICML 2026Newton-coupled Dual-Teacher Semi-supervised Learning Framework
71. ICML 2026NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision
72. ICML 2026Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
73. ICML 2026OCNR: Stabilizing Self-Play by Mitigating Iteration-Collapse With One-Class Novelty Rewards
74. ICML 2026Optimal Self-Consistency for Efficient Reasoning with Large Language Models
75. ICML 2026Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning
76. ICML 2026Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
77. ICML 2026Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning
78. ICML 2026Predicting evolutionary rate as a pretraining task improves genome language model representations
79. ICML 2026Prompt Optimization with Minimal Unlabeled Input via Meta-Reasoning
80. ICML 2026Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
81. ICML 2026Quaternion Self-Attention with Shared Scores
82. ICML 2026R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
83. ICML 2026Reconstruction Outcomes Look Similar but Processes Differ: Improving Context Consistency and Coverage in Graph Masked Auto-Encoder
84. ICML 2026Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
85. ICML 2026RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
86. ICML 2026Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
87. ICML 2026Reinforcement Learning via Self-Distillation
88. ICML 2026Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
89. ICML 2026Rethinking Thinking Tokens: LLMs as Improvement Operators
90. ICML 2026Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
91. ICML 2026RLSF-V: Mitigating Hallucinations in MLLMs via Fuzzy Semantic Self-Feedback
92. ICML 2026Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation
93. ICML 2026Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label
94. ICML 2026Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
95. ICML 2026RSPO: Regularized Self-Play Alignment of Large Language Models
96. ICML 2026SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
97. ICML 2026Scaling Prompt Synthesis for Large Language Model Reasoning
98. ICML 2026Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models
99. ICML 2026Self-Distillation Enables Continual Learning
100. ICML 2026Self-Soupervision: Cooking Model Soups without Labels

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。