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 473 篇，第 2 / 10 页

51. ICLR 2025Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
52. ICLR 2025Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
53. ICLR 2025Backtracking Improves Generation Safety
54. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
55. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
56. ICLR 2025BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
57. ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
58. ICLR 2025Bayesian WeakS-to-Strong from Text Classification to Generation
59. ICLR 2025Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
60. ICLR 2025BingoGuard: LLM Content Moderation Tools with Risk Levels
61. ICLR 2025Black-Box Detection of Language Model Watermarks
62. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
63. ICLR 2025Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
64. ICLR 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
65. ICLR 2025Bootstrapping Language Models with DPO Implicit Rewards
66. ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
67. ICLR 2025Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
68. ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
69. ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
70. ICLR 2025Building Math Agents with Multi-Turn Iterative Preference Learning
71. ICLR 2025Calibrating Expressions of Certainty
72. ICLR 2025Can a Large Language Model be a Gaslighter?
73. ICLR 2025Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
74. ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
75. ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
76. ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
77. ICLR 2025Can We Ignore Labels in Out of Distribution Detection?
78. ICLR 2025Capturing the Temporal Dependence of Training Data Influence
79. ICLR 2025Certified Robustness Under Bounded Levenshtein Distance
80. ICLR 2025Certifying Counterfactual Bias in LLMs
81. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
82. ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
83. ICLR 2025CipherPrune: Efficient and Scalable Private Transformer Inference
84. ICLR 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
85. ICLR 2025Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
86. ICLR 2025CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
87. ICLR 2025Collapsed Language Models Promote Fairness
88. ICLR 2025Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
89. ICLR 2025Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
90. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
91. ICLR 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration
92. ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
93. ICLR 2025Conformal Prediction Sets Can Cause Disparate Impact
94. ICLR 2025Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
95. ICLR 2025Conservative Contextual Bandits: Beyond Linear Representations
96. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
97. ICLR 2025Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis
98. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
99. ICLR 2025Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
100. ICLR 2025Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization

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。