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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 138 | 87 | 101 | 112 | 438 |
| 2024 | 348 | 156 | 246 | 125 | 875 |
| 2025 | 455 | 473 | 300 | 135 | 1,363 |
| 2026 | 480 | 623 | 551 | 228 | 1,882 |
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
- 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 438 篇，第 5 / 9 页
- ICML 2023A Modern Look at the Relationship between Sharpness and Generalization
- ICML 2023A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
- ICML 2023A Study on Transformer Configuration and Training Objective
- ICML 2023A Theoretical Analysis of the Learning Dynamics under Class Imbalance
- ICML 2023abess: A Fast Best-Subset Selection Library in Python and R
- ICML 2023Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations
- ICML 2023Adversarial Classification: Necessary Conditions and Geometric Flows
- ICML 2023Aligning Language Models with Preferences through $f$-divergence Minimization
- ICML 2023Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
- ICML 2023Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
- ICML 2023Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
- ICML 2023Bandit Online Linear Optimization with Hints and Queries
- ICML 2023Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
- ICML 2023Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
- ICML 2023Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
- ICML 2023Constrained Phi-Equilibria
- ICML 2023Contextual Conservative Interleaving Bandits
- ICML 2023Contextual Reliability: When Different Features Matter in Different Contexts
- ICML 2023Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
- ICML 2023Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss
- ICML 2023Cut your Losses with Squentropy
- ICML 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
- ICML 2023DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
- ICML 2023DUET: 2D Structured and Approximately Equivariant Representations
- ICML 2023EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression
- ICML 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
- ICML 2023Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
- ICML 2023Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
- ICML 2023Explainable Data-Driven Optimization: From Context to Decision and Back Again
- ICML 2023FAIRER: Fairness as Decision Rationale Alignment
- ICML 2023Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning
- ICML 2023Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
- ICML 2023Federated Online and Bandit Convex Optimization
- ICML 2023Finding Generalization Measures by Contrasting Signal and Noise
- ICML 2023Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron
- ICML 2023Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond
- ICML 2023Graph Neural Networks with Learnable and Optimal Polynomial Bases
- ICML 2023High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
- ICML 2023How Powerful are Shallow Neural Networks with Bandlimited Random Weights?
- ICML 2023Implicit Jacobian regularization weighted with impurity of probability output
- ICML 2023Incentivizing Exploration with Linear Contexts and Combinatorial Actions
- ICML 2023Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- ICML 2023Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
- ICML 2023Learning Mixtures of Markov Chains and MDPs
- ICML 2023Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence
- ICML 2023Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming
- ICML 2023Meta Optimal Transport
- ICML 2023Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism
- ICML 2023Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals
- ICML 2023Nearly Optimal Competitive Ratio for Online Allocation Problems with Two-sided Resource Constraints and Finite Requests
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"}
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。