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 6 / 9 页
- ICML 2023Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data
- ICML 2023Nonparametric Iterative Machine Teaching
- ICML 2023On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization
- ICML 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
- ICML 2023On Preemption and Learning in Stochastic Scheduling
- ICML 2023On Regularization and Inference with Label Constraints
- ICML 2023On the Functional Similarity of Robust and Non-Robust Neural Representations
- ICML 2023On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
- ICML 2023Online Prototype Alignment for Few-shot Policy Transfer
- ICML 2023Optimal Sets and Solution Paths of ReLU Networks
- ICML 2023Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
- ICML 2023Polarity Is All You Need to Learn and Transfer Faster
- ICML 2023Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
- ICML 2023Project and Forget: Solving Large-Scale Metric Constrained Problems
- ICML 2023Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
- ICML 2023ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
- ICML 2023Provably and Practically Efficient Neural Contextual Bandits
- ICML 2023Regularization-free Diffeomorphic Temporal Alignment Nets
- ICML 2023Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
- ICML 2023Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
- ICML 2023Robust and private stochastic linear bandits
- ICML 2023Robust and Scalable Bayesian Online Changepoint Detection
- ICML 2023Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues
- ICML 2023Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
- ICML 2023Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
- ICML 2023Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm.
- ICML 2023SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance
- ICML 2023Simple Disentanglement of Style and Content in Visual Representations
- ICML 2023SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference
- ICML 2023Spurious Valleys and Clustering Behavior of Neural Networks
- ICML 2023Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
- ICML 2023Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
- ICML 2023Submodular Order Functions and Assortment Optimization
- ICML 2023Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation
- ICML 2023SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
- ICML 2023Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning
- ICML 2023Text-To-Concept (and Back) via Cross-Model Alignment
- ICML 2023The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond
- ICML 2023The SSL Interplay: Augmentations, Inductive Bias, and Generalization
- ICML 2023The Wisdom of Hindsight Makes Language Models Better Instruction Followers
- ICML 2023Thompson Sampling with Less Exploration is Fast and Optimal
- ICML 2023Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
- ICML 2023Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data
- ICML 2023Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts
- ICML 2023Uncertain Evidence in Probabilistic Models and Stochastic Simulators
- ICML 2023Understand and Modularize Generator Optimization in ELECTRA-style Pretraining
- ICML 2023Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
- ICML 2023What Can Be Learnt With Wide Convolutional Neural Networks?
- ICML 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
- ICML 2023When do Minimax-fair Learning and Empirical Risk Minimization Coincide?
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。