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 1,363 篇，第 24 / 28 页

1151. NeurIPS 2025Many LLMs Are More Utilitarian Than One
1152. NeurIPS 2025Matchings Under Biased and Correlated Evaluations
1153. NeurIPS 2025Measuring and Guiding Monosemanticity
1154. NeurIPS 2025Mechanism Design for LLM Fine-tuning with Multiple Reward Models
1155. NeurIPS 2025Median Selection with Noisy and Structural Information
1156. NeurIPS 2025Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
1157. NeurIPS 2025Meta-Learning Objectives for Preference Optimization
1158. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
1159. NeurIPS 2025Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications
1160. NeurIPS 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
1161. NeurIPS 2025Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
1162. NeurIPS 2025Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
1163. NeurIPS 2025Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
1164. NeurIPS 2025MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference
1165. NeurIPS 2025Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
1166. NeurIPS 2025Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One
1167. NeurIPS 2025Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
1168. NeurIPS 2025Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
1169. NeurIPS 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
1170. NeurIPS 2025Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
1171. NeurIPS 2025Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
1172. NeurIPS 2025NeuSymEA: Neuro-symbolic Entity Alignment via Variational Inference
1173. NeurIPS 2025No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
1174. NeurIPS 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
1175. NeurIPS 2025Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
1176. NeurIPS 2025NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
1177. NeurIPS 2025nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
1178. NeurIPS 2025Object-centric binding in Contrastive Language-Image Pretraining
1179. NeurIPS 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
1180. NeurIPS 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
1181. NeurIPS 2025On Evaluating LLM Alignment by Evaluating LLMs as Judges
1182. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
1183. NeurIPS 2025On Local Limits of Sparse Random Graphs: Color Convergence and the Refined Configuration Model
1184. NeurIPS 2025On the creation of narrow AI: hierarchy and nonlocality of neural network skills
1185. NeurIPS 2025On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
1186. NeurIPS 2025On the Existence and Complexity of Core-Stable Data Exchanges
1187. NeurIPS 2025On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels
1188. NeurIPS 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
1189. NeurIPS 2025One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
1190. NeurIPS 2025Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
1191. NeurIPS 2025Online Strategic Classification With Noise and Partial Feedback
1192. NeurIPS 2025OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
1193. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
1194. NeurIPS 2025OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
1195. NeurIPS 2025Orthogonal Contrastive Learning for Multi-Representation fMRI Analysis
1196. NeurIPS 2025OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
1197. NeurIPS 2025Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
1198. NeurIPS 2025OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
1199. NeurIPS 2025Pairwise Calibrated Rewards for Pluralistic Alignment
1200. NeurIPS 2025Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

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。