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 4,558 篇，第 80 / 92 页

3951. NeurIPS 2024MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
3952. NeurIPS 2024Many-shot Jailbreaking
3953. NeurIPS 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
3954. NeurIPS 2024Measuring Goal-Directedness
3955. NeurIPS 2024Measuring Per-Unit Interpretability at Scale Without Humans
3956. NeurIPS 2024MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
3957. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
3958. NeurIPS 2024MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
3959. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
3960. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
3961. NeurIPS 2024Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
3962. NeurIPS 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
3963. NeurIPS 2024MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
3964. NeurIPS 2024MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
3965. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
3966. NeurIPS 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
3967. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
3968. NeurIPS 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
3969. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
3970. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
3971. NeurIPS 2024NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
3972. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs
3973. NeurIPS 2024On Softmax Direct Preference Optimization for Recommendation
3974. NeurIPS 2024On the Adversarial Robustness of Benjamini Hochberg
3975. NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
3976. NeurIPS 2024On the Use of Anchoring for Training Vision Models
3977. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
3978. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
3979. NeurIPS 2024Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
3980. NeurIPS 2024Optimistic Verifiable Training by Controlling Hardware Nondeterminism
3981. NeurIPS 2024Out-Of-Distribution Detection with Diversification (Provably)
3982. NeurIPS 2024Panacea: Pareto Alignment via Preference Adaptation for LLMs
3983. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
3984. NeurIPS 2024PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
3985. NeurIPS 2024Perplexity-aware Correction for Robust Alignment with Noisy Preferences
3986. NeurIPS 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
3987. NeurIPS 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
3988. NeurIPS 2024Policy Aggregation
3989. NeurIPS 2024Predicting the Performance of Foundation Models via Agreement-on-the-Line
3990. NeurIPS 2024Preference Alignment with Flow Matching
3991. NeurIPS 2024Preference Learning Algorithms Do Not Learn Preference Rankings
3992. NeurIPS 2024Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
3993. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
3994. NeurIPS 2024ProgressGym: Alignment with a Millennium of Moral Progress
3995. NeurIPS 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
3996. NeurIPS 2024ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
3997. NeurIPS 2024Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
3998. NeurIPS 2024Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
3999. NeurIPS 2024Provably Safe Neural Network Controllers via Differential Dynamic Logic
4000. NeurIPS 2024PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics

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。