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 1,421 篇，第 23 / 29 页

1101. NeurIPS 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
1102. NeurIPS 2024Learning Human-like Representations to Enable Learning Human Values
1103. NeurIPS 2024Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
1104. NeurIPS 2024Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
1105. NeurIPS 2024Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
1106. NeurIPS 2024Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
1107. NeurIPS 2024LLM Dataset Inference: Did you train on my dataset?
1108. NeurIPS 2024LLM Evaluators Recognize and Favor Their Own Generations
1109. NeurIPS 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
1110. NeurIPS 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
1111. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
1112. NeurIPS 2024Maia-2: A Unified Model for Human-AI Alignment in Chess
1113. NeurIPS 2024MALT Powers Up Adversarial Attacks
1114. NeurIPS 2024MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
1115. NeurIPS 2024Many-shot Jailbreaking
1116. NeurIPS 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
1117. NeurIPS 2024Measuring Goal-Directedness
1118. NeurIPS 2024Measuring Per-Unit Interpretability at Scale Without Humans
1119. NeurIPS 2024MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
1120. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
1121. NeurIPS 2024MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
1122. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
1123. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
1124. NeurIPS 2024Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
1125. NeurIPS 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
1126. NeurIPS 2024MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
1127. NeurIPS 2024MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
1128. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
1129. NeurIPS 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
1130. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
1131. NeurIPS 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
1132. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
1133. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
1134. NeurIPS 2024NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
1135. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs
1136. NeurIPS 2024On Softmax Direct Preference Optimization for Recommendation
1137. NeurIPS 2024On the Adversarial Robustness of Benjamini Hochberg
1138. NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
1139. NeurIPS 2024On the Use of Anchoring for Training Vision Models
1140. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
1141. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
1142. NeurIPS 2024Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
1143. NeurIPS 2024Optimistic Verifiable Training by Controlling Hardware Nondeterminism
1144. NeurIPS 2024Out-Of-Distribution Detection with Diversification (Provably)
1145. NeurIPS 2024Panacea: Pareto Alignment via Preference Adaptation for LLMs
1146. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
1147. NeurIPS 2024PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
1148. NeurIPS 2024Perplexity-aware Correction for Robust Alignment with Noisy Preferences
1149. NeurIPS 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
1150. NeurIPS 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

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。