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 246 篇，第 2 / 5 页

51. ICML 2024Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
52. ICML 2024Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
53. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
54. ICML 2024Detecting and Identifying Selection Structure in Sequential Data
55. ICML 2024Differentiability and Optimization of Multiparameter Persistent Homology
56. ICML 2024Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
57. ICML 2024Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
58. ICML 2024Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
59. ICML 2024Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset
60. ICML 2024Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
61. ICML 2024EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
62. ICML 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
63. ICML 2024Emergent Equivariance in Deep Ensembles
64. ICML 2024Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
65. ICML 2024Enhancing Implicit Shape Generators Using Topological Regularizations
66. ICML 2024Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models
67. ICML 2024Equivariant Deep Weight Space Alignment
68. ICML 2024Equivariant Frames and the Impossibility of Continuous Canonicalization
69. ICML 2024Estimating Barycenters of Distributions with Neural Optimal Transport
70. ICML 2024Estimating Canopy Height at Scale
71. ICML 2024Expand-and-Cluster: Parameter Recovery of Neural Networks
72. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
73. ICML 2024Exploring the LLM Journey from Cognition to Expression with Linear Representations
74. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
75. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
76. ICML 2024FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
77. ICML 2024FESSNC: Fast Exponentially Stable and Safe Neural Controller
78. ICML 2024Flextron: Many-in-One Flexible Large Language Model
79. ICML 2024From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
80. ICML 2024Fundamental Limitations of Alignment in Large Language Models
81. ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
82. ICML 2024GNNs Also Deserve Editing, and They Need It More Than Once
83. ICML 2024Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
84. ICML 2024GRATH: Gradual Self-Truthifying for Large Language Models
85. ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
86. ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
87. ICML 2024High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost
88. ICML 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
89. ICML 2024How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
90. ICML 2024How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
91. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
92. ICML 2024IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
93. ICML 2024Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
94. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
95. ICML 2024Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
96. ICML 2024Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
97. ICML 2024In-Context Language Learning: Architectures and Algorithms
98. ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
99. ICML 2024InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
100. ICML 2024Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification

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。