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 1,339 篇，第 26 / 27 页
- ICLR 2024ZeRO++: Extremely Efficient Collective Communication for Large Model Training
- ICLR 2024Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
- ICLR 2023$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
- ICLR 2023A Differential Geometric View and Explainability of GNN on Evolving Graphs
- ICLR 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming
- ICLR 2023A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond
- ICLR 2023A Message Passing Perspective on Learning Dynamics of Contrastive Learning
- ICLR 2023Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
- ICLR 2023Almost Linear Constant-Factor Sketching for $\ell_1$ and Logistic Regression
- ICLR 2023Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks
- ICLR 2023Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing
- ICLR 2023Auto-Encoding Goodness of Fit
- ICLR 2023BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS
- ICLR 2023BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion
- ICLR 2023Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD
- ICLR 2023Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens
- ICLR 2023Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization
- ICLR 2023Compressing multidimensional weather and climate data into neural networks
- ICLR 2023ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond
- ICLR 2023DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity
- ICLR 2023Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
- ICLR 2023Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization
- ICLR 2023Discovering Latent Knowledge in Language Models Without Supervision
- ICLR 2023Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
- ICLR 2023Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- ICLR 2023Efficient approximation of neural population structure and correlations with probabilistic circuits
- ICLR 2023Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution
- ICLR 2023Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
- ICLR 2023FaiREE: fair classification with finite-sample and distribution-free guarantee
- ICLR 2023Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- ICLR 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
- ICLR 2023Generalization and Estimation Error Bounds for Model-based Neural Networks
- ICLR 2023Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
- ICLR 2023Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
- ICLR 2023Git Re-Basin: Merging Models modulo Permutation Symmetries
- ICLR 2023How I Learned to Stop Worrying and Love Retraining
- ICLR 2023Human alignment of neural network representations
- ICLR 2023Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting
- ICLR 2023LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
- ICLR 2023Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes
- ICLR 2023Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
- ICLR 2023Mind's Eye: Grounded Language Model Reasoning through Simulation
- ICLR 2023MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC
- ICLR 2023Multiple sequence alignment as a sequence-to-sequence learning problem
- ICLR 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
- ICLR 2023Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be
- ICLR 2023On Accelerated Perceptrons and Beyond
- ICLR 2023On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
- ICLR 2023On the duality between contrastive and non-contrastive self-supervised learning
- ICLR 2023On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations
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。