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 87 篇，第 2 / 2 页

51. ICLR 2023Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment
52. ICLR 2023PASHA: Efficient HPO and NAS with Progressive Resource Allocation
53. ICLR 2023Personalized Federated Learning with Feature Alignment and Classifier Collaboration
54. ICLR 2023PiFold: Toward effective and efficient protein inverse folding
55. ICLR 2023Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics
56. ICLR 2023Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
57. ICLR 2023Reliability of CKA as a Similarity Measure in Deep Learning
58. ICLR 2023Restricted Strong Convexity of Deep Learning Models with Smooth Activations
59. ICLR 2023Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL
60. ICLR 2023Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
61. ICLR 2023Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions
62. ICLR 2023Semi-Parametric Inducing Point Networks and Neural Processes
63. ICLR 2023Simple and Scalable Nearest Neighbor Machine Translation
64. ICLR 2023Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
65. ICLR 2023Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
66. ICLR 2023Sparse Mixture-of-Experts are Domain Generalizable Learners
67. ICLR 2023Stochastic Differentially Private and Fair Learning
68. ICLR 2023Supervision Complexity and its Role in Knowledge Distillation
69. ICLR 2023Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow
70. ICLR 2023SYNC: SAFETY-AWARE NEURAL CONTROL FOR STABILIZING STOCHASTIC DELAY-DIFFERENTIAL EQUATIONS
71. ICLR 2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
72. ICLR 2023Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
73. ICLR 2023Task Ambiguity in Humans and Language Models
74. ICLR 2023TempCLR: Temporal Alignment Representation with Contrastive Learning
75. ICLR 2023Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations
76. ICLR 2023Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case
77. ICLR 2023Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
78. ICLR 2023Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
79. ICLR 2023Training language models to summarize narratives improves brain alignment
80. ICLR 2023Understanding Influence Functions and Datamodels via Harmonic Analysis
81. ICLR 2023Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
82. ICLR 2023Unsupervised Manifold Alignment with Joint Multidimensional Scaling
83. ICLR 2023Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
84. ICLR 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutions
85. ICLR 2023When to Make and Break Commitments?
86. ICLR 2023Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
87. ICLR 2023Why (and When) does Local SGD Generalize Better than SGD?

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。