对齐与安全论文趋势 2023–2026

RLHF、偏好优化、红队与安全对齐

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 4,558 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

对齐与安全论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202313887101112438
2024348156246125875
20254554733001351,363
20264806235512281,882

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

全部对齐与安全论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 4,558 篇，第 86 / 92 页

  1. ICLR 2023Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
  2. ICLR 2023Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization
  3. ICLR 2023Discovering Latent Knowledge in Language Models Without Supervision
  4. ICLR 2023Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
  5. ICLR 2023Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
  6. ICLR 2023Efficient approximation of neural population structure and correlations with probabilistic circuits
  7. ICLR 2023Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution
  8. ICLR 2023Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
  9. ICLR 2023FaiREE: fair classification with finite-sample and distribution-free guarantee
  10. ICLR 2023Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
  11. ICLR 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
  12. ICLR 2023Generalization and Estimation Error Bounds for Model-based Neural Networks
  13. ICLR 2023Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
  14. ICLR 2023Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
  15. ICLR 2023Git Re-Basin: Merging Models modulo Permutation Symmetries
  16. ICLR 2023How I Learned to Stop Worrying and Love Retraining
  17. ICLR 2023Human alignment of neural network representations
  18. ICLR 2023Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting
  19. ICLR 2023LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
  20. ICLR 2023Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes
  21. ICLR 2023Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
  22. ICLR 2023Mind's Eye: Grounded Language Model Reasoning through Simulation
  23. ICLR 2023MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC
  24. ICLR 2023Multiple sequence alignment as a sequence-to-sequence learning problem
  25. ICLR 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
  26. ICLR 2023Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be
  27. ICLR 2023On Accelerated Perceptrons and Beyond
  28. ICLR 2023On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
  29. ICLR 2023On the duality between contrastive and non-contrastive self-supervised learning
  30. ICLR 2023On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations
  31. ICLR 2023One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks
  32. ICLR 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
  33. ICLR 2023Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment
  34. ICLR 2023PASHA: Efficient HPO and NAS with Progressive Resource Allocation
  35. ICLR 2023Personalized Federated Learning with Feature Alignment and Classifier Collaboration
  36. ICLR 2023PiFold: Toward effective and efficient protein inverse folding
  37. ICLR 2023Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics
  38. ICLR 2023Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
  39. ICLR 2023Reliability of CKA as a Similarity Measure in Deep Learning
  40. ICLR 2023Restricted Strong Convexity of Deep Learning Models with Smooth Activations
  41. ICLR 2023Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL
  42. ICLR 2023Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
  43. ICLR 2023Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions
  44. ICLR 2023Semi-Parametric Inducing Point Networks and Neural Processes
  45. ICLR 2023Simple and Scalable Nearest Neighbor Machine Translation
  46. ICLR 2023Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
  47. ICLR 2023Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
  48. ICLR 2023Sparse Mixture-of-Experts are Domain Generalizable Learners
  49. ICLR 2023Stochastic Differentially Private and Fair Learning
  50. ICLR 2023Supervision Complexity and its Role in Knowledge Distillation

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 查对齐与安全在 NeurIPS 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": "alignment-and-safety"}

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对齐与安全论文？
共 4,558 篇，按年份分别是 2023 年 438 篇、2024 年 875 篇、2025 年 1,363 篇、2026 年 1,882 篇。
NeurIPS 2026 有多少篇对齐与安全论文？
NeurIPS 2026 有 480 篇对齐与安全论文，上一届是 455 篇。
ICLR 2026 有多少篇对齐与安全论文？
ICLR 2026 有 623 篇对齐与安全论文，上一届是 473 篇。
ICML 2026 有多少篇对齐与安全论文？
ICML 2026 有 551 篇对齐与安全论文，上一届是 300 篇。
CVPR 2026 有多少篇对齐与安全论文？
CVPR 2026 有 228 篇对齐与安全论文，上一届是 135 篇。
哪个会议的对齐与安全论文最多？
NeurIPS，2023–2026 年共 1,421 篇。

「对齐与负责任 AI」下的其他主题