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 1,956 篇，第 9 / 40 页

401. ICML 2026SpikeCLR: Self-Supervised Contrastive Learning for Visual Representations with Spiking Neural Networks
402. ICML 2026Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
403. ICML 2026SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
404. ICML 2026STAND: Self-Aware Precondition Induction for Interactive Task Learning
405. ICML 2026Structure Enables Effective Self-Localization of Errors in LLMs
406. ICML 2026Supervised Graph Contrastive Learning for Gene Regulatory Networks
407. ICML 2026SURF: Separation via Unsupervised Remixing Flow
408. ICML 2026TabularBERT: Binning-Based Self-Supervised Learning for Tabular Representation
409. ICML 2026The Extra Tokens Matter: Disentangled Representation Learning with Vision Transformers
410. ICML 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
411. ICML 2026The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
412. ICML 2026The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
413. ICML 2026TMS: Trajectory-Mixed Supervision for On-Policy Self Distillation
414. ICML 2026Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
415. ICML 2026TriForces: Augmenting Atomistic GNNs for Transferable Representations
416. ICML 2026Understanding Self-Supervised Learning via Latent Distribution Matching
417. ICML 2026USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning
418. ICML 2026Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture – Bridging Predictive and Generative Self-Supervised Learning
419. ICML 2026Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention
420. ICML 2026VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
421. ICML 2026Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
422. ICML 2026When Softmax Fails at the Top: Extreme‑Value Corrections for InfoNCE
423. NeurIPS 20263D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
424. NeurIPS 2026AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
425. NeurIPS 2026ASH: Agents that Self-Hone via Embodied Learning
426. NeurIPS 2026Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
427. NeurIPS 2026AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
428. NeurIPS 2026Auditing Single-Query Recoverability in Self-Supervised Representations
429. NeurIPS 2026Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
430. NeurIPS 2026BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial Training
431. NeurIPS 2026BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
432. NeurIPS 2026Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline
433. NeurIPS 2026Beyond Correctness: Robustness-Driven Evolutionary Self-Training for Large Language Models
434. NeurIPS 2026Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
435. NeurIPS 2026Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View Generation
436. NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
437. NeurIPS 2026Cache the Future: Training-Free Self-Revision for Diffusion Transformer Acceleration
438. NeurIPS 2026Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production
439. NeurIPS 2026CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification
440. NeurIPS 2026Closing the Loop with Fixed-Point Self-Attention
441. NeurIPS 2026Coherence Mechanisms for Provable Self-Improvement
442. NeurIPS 2026CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation
443. NeurIPS 2026D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
444. NeurIPS 2026DAGA: Dynamic Attention-Guided Adaptation for Self-Supervised Vision Transformers
445. NeurIPS 2026Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student
446. NeurIPS 2026DeGlare: Self-Supervised Specular Removal for Industrial Metallic Surfaces via Multi-Illumination Priors
447. NeurIPS 2026Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
448. NeurIPS 2026Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
449. NeurIPS 2026Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers
450. NeurIPS 2026EvoGround: Self-Evolving Video Agents for Video Temporal Grounding

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。