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 348 篇，第 4 / 7 页

151. NeurIPS 2024Invisible Image Watermarks Are Provably Removable Using Generative AI
152. NeurIPS 2024Iterative Reasoning Preference Optimization
153. NeurIPS 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
154. NeurIPS 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
155. NeurIPS 2024Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
156. NeurIPS 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
157. NeurIPS 2024Kernel PCA for Out-of-Distribution Detection
158. NeurIPS 2024Label Alignment Regularization for Distribution Shift
159. NeurIPS 2024LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
160. NeurIPS 2024LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
161. NeurIPS 2024Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
162. NeurIPS 2024Large Language Model Unlearning
163. NeurIPS 2024Large Language Model Unlearning via Embedding-Corrupted Prompts
164. NeurIPS 2024Large language model validity via enhanced conformal prediction methods
165. NeurIPS 2024Latent Functional Maps: a spectral framework for representation alignment
166. NeurIPS 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
167. NeurIPS 2024Learning Human-like Representations to Enable Learning Human Values
168. NeurIPS 2024Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
169. NeurIPS 2024Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
170. NeurIPS 2024Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
171. NeurIPS 2024Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
172. NeurIPS 2024LLM Dataset Inference: Did you train on my dataset?
173. NeurIPS 2024LLM Evaluators Recognize and Favor Their Own Generations
174. NeurIPS 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
175. NeurIPS 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
176. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
177. NeurIPS 2024Maia-2: A Unified Model for Human-AI Alignment in Chess
178. NeurIPS 2024MALT Powers Up Adversarial Attacks
179. NeurIPS 2024MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
180. NeurIPS 2024Many-shot Jailbreaking
181. NeurIPS 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
182. NeurIPS 2024Measuring Goal-Directedness
183. NeurIPS 2024Measuring Per-Unit Interpretability at Scale Without Humans
184. NeurIPS 2024MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
185. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
186. NeurIPS 2024MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
187. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
188. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
189. NeurIPS 2024Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
190. NeurIPS 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
191. NeurIPS 2024MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
192. NeurIPS 2024MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
193. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
194. NeurIPS 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
195. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
196. NeurIPS 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
197. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
198. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
199. NeurIPS 2024NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
200. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs

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。