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 101 篇，第 2 / 3 页

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

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。