深度学习 · self supervised learning论文趋势 2023–2026

ICML/NeurIPS 深度学习方向：self_supervised_learning

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,958 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

深度学习 · self supervised learning论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202316010841146455
202411019562105472
20251471957283497
202611019513594534

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

全部深度学习 · self supervised learning论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 195 篇，第 4 / 4 页

  1. ICLR 2025SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal Coordination
  2. ICLR 2025SoftCVI: Contrastive variational inference with self-generated soft labels
  3. ICLR 2025SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
  4. ICLR 2025SparsyFed: Sparse Adaptive Federated Learning
  5. ICLR 2025Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
  6. ICLR 2025Spherical Tree-Sliced Wasserstein Distance
  7. ICLR 2025SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
  8. ICLR 2025SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised Learning
  9. ICLR 2025ST-GCond: Self-supervised and Transferable Graph Dataset Condensation
  10. ICLR 2025Sylber: Syllabic Embedding Representation of Speech from Raw Audio
  11. ICLR 2025T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
  12. ICLR 2025The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities
  13. ICLR 2025The Belief State Transformer
  14. ICLR 2025The Pitfalls of Memorization: When Memorization Hurts Generalization
  15. ICLR 2025Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
  16. ICLR 2025Three Mechanisms of Feature Learning in a Linear Network
  17. ICLR 2025Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
  18. ICLR 2025Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
  19. ICLR 2025Towards a learning theory of representation alignment
  20. ICLR 2025Towards Calibrated Deep Clustering Network
  21. ICLR 2025Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
  22. ICLR 2025Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression
  23. ICLR 2025Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
  24. ICLR 2025Training Language Models to Self-Correct via Reinforcement Learning
  25. ICLR 2025Training Neural Networks as Recognizers of Formal Languages
  26. ICLR 2025Training One-Dimensional Graph Neural Networks is NP-Hard
  27. ICLR 2025Transformer Learns Optimal Variable Selection in Group-Sparse Classification
  28. ICLR 2025Transformer Meets Twicing: Harnessing Unattended Residual Information
  29. ICLR 2025Understanding the Stability-based Generalization of Personalized Federated Learning
  30. ICLR 2025Unifying Causal Representation Learning with the Invariance Principle
  31. ICLR 2025UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation
  32. ICLR 2025Universal Image Restoration Pre-training via Degradation Classification
  33. ICLR 2025Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints
  34. ICLR 2025Unsupervised Model Tree Heritage Recovery
  35. ICLR 2025Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation
  36. ICLR 2025UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate
  37. ICLR 2025URLOST: Unsupervised Representation Learning without Stationarity or Topology
  38. ICLR 2025Vector-ICL: In-context Learning with Continuous Vector Representations
  39. ICLR 2025Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
  40. ICLR 2025WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning
  41. ICLR 2025WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
  42. ICLR 2025Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
  43. ICLR 2025What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
  44. ICLR 2025What to align in multimodal contrastive learning?
  45. ICLR 2025Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查深度学习 · self supervised learning在 ICLR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dl-self-supervised-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「深度学习」下的其他主题