对齐与安全论文趋势 2023–2026

主要结论

• 对齐与安全论文从 2023 年的 438 篇增长到 2026 年的 1,882 篇，三年间扩大到约 4.3 倍。
• NeurIPS 是发对齐与安全论文最多的会议，2023–2026 年共 1,421 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是社会层面 · safety：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 137 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的社会层面 · safety是 93 倍，对齐与安全是 4.3 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 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
• ICML 2026AICrypto: Evaluating Cryptography Capabilities of Large Language Models
• ICLR 2026A Fair Bayesian Inference through Matched Gibbs Posterior
• CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and
• NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
• ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
• ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
• CVPR 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models
• NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
• ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
• ICLR 2024A unique M-pattern for micro-expression spotting in long videos
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
• ICLR 2023Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
• CVPR 2023Adjustment and Alignment for Unbiased Open Set Domain Adaptation
• NeurIPS 2026$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
• ICML 2026Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
• ICLR 2026A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
• CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

全部对齐与安全论文

共 138 篇，第 1 / 3 页

1. NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
2. NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
3. NeurIPS 2023[Re] VAE Approximation Error: ELBO and Exponential Families
4. NeurIPS 2023A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
5. NeurIPS 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
6. NeurIPS 2023A Spectral Theory of Neural Prediction and Alignment
7. NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
8. NeurIPS 2023Alignment with human representations supports robust few-shot learning
9. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
10. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
11. NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
12. NeurIPS 2023Behavior Alignment via Reward Function Optimization
13. NeurIPS 2023Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
14. NeurIPS 2023Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
15. NeurIPS 2023Bridging Discrete and Backpropagation: Straight-Through and Beyond
16. NeurIPS 2023Cascading Contextual Assortment Bandits
17. NeurIPS 2023Closing the gap between the upper bound and lower bound of Adam's iteration complexity
18. NeurIPS 2023Collaborative Alignment of NLP Models
19. NeurIPS 2023Convex and Non-convex Optimization Under Generalized Smoothness
20. NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
21. NeurIPS 2023Data-Driven Network Neuroscience: On Data Collection and Benchmark
22. NeurIPS 2023Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
23. NeurIPS 2023Degraded Polygons Raise Fundamental Questions of Neural Network Perception
24. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
25. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
26. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
27. NeurIPS 2023Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
28. NeurIPS 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
29. NeurIPS 2023Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
30. NeurIPS 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
31. NeurIPS 2023Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
32. NeurIPS 2023Exact Verification of ReLU Neural Control Barrier Functions
33. NeurIPS 2023Expert load matters: operating networks at high accuracy and low manual effort
34. NeurIPS 2023Explainable and Efficient Randomized Voting Rules
35. NeurIPS 2023Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
36. NeurIPS 2023Fast and Simple Spectral Clustering in Theory and Practice
37. NeurIPS 2023FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning
38. NeurIPS 2023Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
39. NeurIPS 2023Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
40. NeurIPS 2023GALOPA: Graph Transport Learning with Optimal Plan Alignment
41. NeurIPS 2023Generalized equivalences between subsampling and ridge regularization
42. NeurIPS 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
43. NeurIPS 2023Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
44. NeurIPS 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
45. NeurIPS 2023Honesty Is the Best Policy: Defining and Mitigating AI Deception
46. NeurIPS 2023Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
47. NeurIPS 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
48. NeurIPS 2023Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
49. NeurIPS 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
50. NeurIPS 2023IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

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。