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 246 篇，第 5 / 5 页

  1. ICML 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
  2. ICML 2024SelfIE: Self-Interpretation of Large Language Model Embeddings
  3. ICML 2024Simultaneous identification of models and parameters of scientific simulators
  4. ICML 2024SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
  5. ICML 2024Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence
  6. ICML 2024Sobolev Space Regularised Pre Density Models
  7. ICML 2024SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity
  8. ICML 2024Sparse and Structured Hopfield Networks
  9. ICML 2024Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
  10. ICML 2024Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models
  11. ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
  12. ICML 2024SqueezeLLM: Dense-and-Sparse Quantization
  13. ICML 2024Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations
  14. ICML 2024Stacking Deep Set Networks and Pooling by Quantiles
  15. ICML 2024STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment
  16. ICML 2024StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
  17. ICML 2024Symmetry Induces Structure and Constraint of Learning
  18. ICML 2024Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
  19. ICML 2024Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
  20. ICML 2024The Computational Complexity of Finding Second-Order Stationary Points
  21. ICML 2024The Entropy Enigma: Success and Failure of Entropy Minimization
  22. ICML 2024The Good, The Bad, and Why: Unveiling Emotions in Generative AI
  23. ICML 2024The Linear Representation Hypothesis and the Geometry of Large Language Models
  24. ICML 2024Token-level Direct Preference Optimization
  25. ICML 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
  26. ICML 2024Topological Neural Networks go Persistent, Equivariant, and Continuous
  27. ICML 2024Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components
  28. ICML 2024Towards Efficient Exact Optimization of Language Model Alignment
  29. ICML 2024Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
  30. ICML 2024Towards Modular LLMs by Building and Reusing a Library of LoRAs
  31. ICML 2024Towards Scalable and Versatile Weight Space Learning
  32. ICML 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
  33. ICML 2024Transformers, parallel computation, and logarithmic depth
  34. ICML 2024Transforming and Combining Rewards for Aligning Large Language Models
  35. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
  36. ICML 2024Understanding MLP-Mixer as a wide and sparse MLP
  37. ICML 2024Understanding the Learning Dynamics of Alignment with Human Feedback
  38. ICML 2024Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
  39. ICML 2024Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
  40. ICML 2024Verifying message-passing neural networks via topology-based bounds tightening
  41. ICML 2024WARM: On the Benefits of Weight Averaged Reward Models
  42. ICML 2024Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
  43. ICML 2024Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
  44. ICML 2024What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
  45. ICML 2024When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
  46. ICML 2024When Will Gradient Regularization Be Harmful?

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