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 497 篇，第 9 / 10 页

401. NeurIPS 2025GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
402. NeurIPS 2025Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
403. NeurIPS 2025How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning
404. NeurIPS 2025How to build a consistency model: Learning flow maps via self-distillation
405. NeurIPS 2025Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
406. NeurIPS 2025InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
407. NeurIPS 2025Is Limited Participant Diversity Impeding EEG-based Machine Learning?
408. NeurIPS 2025Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
409. NeurIPS 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
410. NeurIPS 2025Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning
411. NeurIPS 2025KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing
412. NeurIPS 2025Know Thyself by Knowing Others: Learning Neuron Identity from Population Context
413. NeurIPS 2025Language Models can Self-Improve at State-Value Estimation for Better Search
414. NeurIPS 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
415. NeurIPS 2025Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
416. NeurIPS 2025Let LRMs Break Free from Overthinking via Self-Braking Tuning
417. NeurIPS 2025LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
418. NeurIPS 2025LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
419. NeurIPS 2025LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
420. NeurIPS 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning
421. NeurIPS 2025Mitigating Spurious Features in Contrastive Learning with Spectral Regularization
422. NeurIPS 2025MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes
423. NeurIPS 2025‌Navigating the MIL Trade-Off: Flexible Pooling for Whole Slide Image Classification
424. NeurIPS 2025Neurons as Detectors of Coherent Sets in Sensory Dynamics
425. NeurIPS 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
426. NeurIPS 2025OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild
427. NeurIPS 2025On Agnostic PAC Learning in the Small Error Regime
428. NeurIPS 2025On the Role of Hidden States of Modern Hopfield Network in Transformer
429. NeurIPS 2025OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation
430. NeurIPS 2025Path-Enhanced Contrastive Learning for Recommendation
431. NeurIPS 2025PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
432. NeurIPS 2025PIVNO: Particle Image Velocimetry Neural Operator
433. NeurIPS 2025Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
434. NeurIPS 2025Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
435. NeurIPS 2025QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
436. NeurIPS 2025QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation
437. NeurIPS 2025Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights
438. NeurIPS 2025RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
439. NeurIPS 2025Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians
440. NeurIPS 2025Revisiting Semi-Supervised Learning in the Era of Foundation Models
441. NeurIPS 2025RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
442. NeurIPS 2025Robust Minimax Boosting with Performance Guarantees
443. NeurIPS 2025Scalable Best-of-N Selection for Large Language Models via Self-Certainty
444. NeurIPS 2025SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
445. NeurIPS 2025SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
446. NeurIPS 2025Self Iterative Label Refinement via Robust Unlabeled Learning
447. NeurIPS 2025Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential
448. NeurIPS 2025Self-Adapting Language Models
449. NeurIPS 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
450. NeurIPS 2025Self-diffusion for Solving Inverse Problems

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。