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 4 / 10 页

151. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
152. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
153. ICLR 2025Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer
154. ICLR 2025ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
155. ICLR 2025EvA: Erasing Spurious Correlations with Activations
156. ICLR 2025Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
157. ICLR 2025Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes
158. ICLR 2025Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm
159. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
160. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
161. ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
162. ICLR 2025Fair Clustering in the Sliding Window Model
163. ICLR 2025FairDen: Fair Density-Based Clustering
164. ICLR 2025FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
165. ICLR 2025Fantastic Copyrighted Beasts and How (Not) to Generate Them
166. ICLR 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
167. ICLR 2025Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
168. ICLR 2025Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
169. ICLR 2025Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
170. ICLR 2025FormalAlign: Automated Alignment Evaluation for Autoformalization
171. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
172. ICLR 2025From Search to Sampling: Generative Models for Robust Algorithmic Recourse
173. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
174. ICLR 2025Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation
175. ICLR 2025GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
176. ICLR 2025Generalization and Distributed Learning of GFlowNets
177. ICLR 2025Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
178. ICLR 2025Generative Classifiers Avoid Shortcut Solutions
179. ICLR 2025Generative Monoculture in Large Language Models
180. ICLR 2025Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
181. ICLR 2025Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume Minimization
182. ICLR 2025GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring
183. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
184. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
185. ICLR 2025Gramian Multimodal Representation Learning and Alignment
186. ICLR 2025Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
187. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
188. ICLR 2025Guaranteed Generation from Large Language Models
189. ICLR 2025Gyrogroup Batch Normalization
190. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
191. ICLR 2025HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS
192. ICLR 2025HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
193. ICLR 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
194. ICLR 2025Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
195. ICLR 2025HelpSteer2-Preference: Complementing Ratings with Preferences
196. ICLR 2025HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
197. ICLR 2025Hessian-Free Online Certified Unlearning
198. ICLR 2025Higher-Order Graphon Neural Networks: Approximation and Cut Distance
199. ICLR 2025How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
200. ICLR 2025How Far Are We from True Unlearnability?

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。