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 195 篇，第 4 / 4 页

151. ICLR 2026Self-Supervised Learning from Structural Invariance
152. ICLR 2026Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
153. ICLR 2026Semi-Supervised Preference Optimization with Limited Feedback
154. ICLR 2026SigLIP-HD by Fine-to-Coarse Supervision
155. ICLR 2026SkillFactory: Self-Distillation for Learning Cognitive Behaviors
156. ICLR 2026SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
157. ICLR 2026SNAPHARD CONTRAST LEARNING
158. ICLR 2026Soft Equivariance Regularization for Invariant Self-Supervised Learning
159. ICLR 2026Softmax is not Enough (for Adaptive Conformal Classification)
160. ICLR 2026Spectral Attention Steering for Prompt Highlighting
161. ICLR 2026Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
162. ICLR 2026Splat Regression Models
163. ICLR 2026ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
164. ICLR 2026Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
165. ICLR 2026t-SNE Exaggerates Clusters, Provably
166. ICLR 2026Temporal Slowness in Central Vision Drives Semantic Object Learning
167. ICLR 2026THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCE
168. ICLR 2026There Was Never a Bottleneck in Concept Bottleneck Models
169. ICLR 2026Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
170. ICLR 2026To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
171. ICLR 2026Token Distillation: Attention-Aware Input Embeddings for New Tokens
172. ICLR 2026Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
173. ICLR 2026Toward Principled Flexible Scaling for Self-Gated Neural Activation
174. ICLR 2026Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
175. ICLR 2026Towards Improved Sentence Representations using Token Graphs
176. ICLR 2026Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
177. ICLR 2026TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
178. ICLR 2026TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning
179. ICLR 2026TRIDENT: Cross-Domain Trajectory Spatio-Temporal Representation via Distance-Preserving Triplet Learning
180. ICLR 2026True Self-Supervised Novel View Synthesis is Transferable
181. ICLR 2026TS-DDAE: A novel Temporal-Spectral Denoising Diffusion AutoEncoder for Wireless Signal Recognition Model Pre-training
182. ICLR 2026Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
183. ICLR 2026Understanding the Learning Phases in Self-Supervised Learning via Critical Periods
184. ICLR 2026Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
185. ICLR 2026UniOD: A Universal Model for Outlier Detection across Diverse Domains
186. ICLR 2026Universal Beta Splatting
187. ICLR 2026Unlearning Evaluation through Subset Statistical Independence
188. ICLR 2026Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
189. ICLR 2026Unsupervised Representation Learning - an Invariant Risk Minimization Perspective
190. ICLR 2026Variational Inference for Cyclic Learning
191. ICLR 2026VideoAgentTrek: Computer-Use Pretraining from Unlabeled Videos
192. ICLR 2026Visual Jigsaw Post-Training Improves MLLMs
193. ICLR 2026Weight Space Representation Learning on Diverse NeRF Architectures
194. ICLR 2026Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
195. ICLR 2026Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders

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。