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 89 / 92 页

  1. ICML 2023Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
  2. ICML 2023Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
  3. ICML 2023Submodular Order Functions and Assortment Optimization
  4. ICML 2023Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation
  5. ICML 2023SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
  6. ICML 2023Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning
  7. ICML 2023Text-To-Concept (and Back) via Cross-Model Alignment
  8. ICML 2023The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond
  9. ICML 2023The SSL Interplay: Augmentations, Inductive Bias, and Generalization
  10. ICML 2023The Wisdom of Hindsight Makes Language Models Better Instruction Followers
  11. ICML 2023Thompson Sampling with Less Exploration is Fast and Optimal
  12. ICML 2023Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
  13. ICML 2023Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data
  14. ICML 2023Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts
  15. ICML 2023Uncertain Evidence in Probabilistic Models and Stochastic Simulators
  16. ICML 2023Understand and Modularize Generator Optimization in ELECTRA-style Pretraining
  17. ICML 2023Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
  18. ICML 2023What Can Be Learnt With Wide Convolutional Neural Networks?
  19. ICML 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
  20. ICML 2023When do Minimax-fair Learning and Empirical Risk Minimization Coincide?
  21. NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
  22. NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
  23. NeurIPS 2023[Re] VAE Approximation Error: ELBO and Exponential Families
  24. NeurIPS 2023A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
  25. NeurIPS 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
  26. NeurIPS 2023A Spectral Theory of Neural Prediction and Alignment
  27. NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
  28. NeurIPS 2023Alignment with human representations supports robust few-shot learning
  29. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
  30. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
  31. NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
  32. NeurIPS 2023Behavior Alignment via Reward Function Optimization
  33. NeurIPS 2023Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
  34. NeurIPS 2023Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
  35. NeurIPS 2023Bridging Discrete and Backpropagation: Straight-Through and Beyond
  36. NeurIPS 2023Cascading Contextual Assortment Bandits
  37. NeurIPS 2023Closing the gap between the upper bound and lower bound of Adam's iteration complexity
  38. NeurIPS 2023Collaborative Alignment of NLP Models
  39. NeurIPS 2023Convex and Non-convex Optimization Under Generalized Smoothness
  40. NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
  41. NeurIPS 2023Data-Driven Network Neuroscience: On Data Collection and Benchmark
  42. NeurIPS 2023Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
  43. NeurIPS 2023Degraded Polygons Raise Fundamental Questions of Neural Network Perception
  44. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
  45. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  46. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
  47. NeurIPS 2023Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
  48. NeurIPS 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
  49. NeurIPS 2023Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
  50. NeurIPS 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

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