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 21 / 29 页

1001. NeurIPS 2024Conformalized Multiple Testing after Data-dependent Selection
1002. NeurIPS 2024Conformalized Time Series with Semantic Features
1003. NeurIPS 2024Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
1004. NeurIPS 2024Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
1005. NeurIPS 2024Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
1006. NeurIPS 2024Contextual Bilevel Reinforcement Learning for Incentive Alignment
1007. NeurIPS 2024Continual Learning with Global Alignment
1008. NeurIPS 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
1009. NeurIPS 2024Cross-Modality Perturbation Synergy Attack for Person Re-identification
1010. NeurIPS 2024DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
1011. NeurIPS 2024DarkSAM: Fooling Segment Anything Model to Segment Nothing
1012. NeurIPS 2024DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
1013. NeurIPS 2024Data Free Backdoor Attacks
1014. NeurIPS 2024Decoding-Time Language Model Alignment with Multiple Objectives
1015. NeurIPS 2024Deep Learning in Medical Image Registration: Magic or Mirage?
1016. NeurIPS 2024DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
1017. NeurIPS 2024DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
1018. NeurIPS 2024DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
1019. NeurIPS 2024Diffusion Models are Certifiably Robust Classifiers
1020. NeurIPS 2024Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
1021. NeurIPS 2024DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
1022. NeurIPS 2024Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
1023. NeurIPS 2024Discovering Preference Optimization Algorithms with and for Large Language Models
1024. NeurIPS 2024Distributional Preference Alignment of LLMs via Optimal Transport
1025. NeurIPS 2024Distributionally Robust Performative Prediction
1026. NeurIPS 2024DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
1027. NeurIPS 2024DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
1028. NeurIPS 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
1029. NeurIPS 2024EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
1030. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
1031. NeurIPS 2024Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
1032. NeurIPS 2024EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
1033. NeurIPS 2024Empowering and Assessing the Utility of Large Language Models in Crop Science
1034. NeurIPS 2024Energy-based Hopfield Boosting for Out-of-Distribution Detection
1035. NeurIPS 2024Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
1036. NeurIPS 2024Enhancing Large Vision Language Models with Self-Training on Image Comprehension
1037. NeurIPS 2024Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
1038. NeurIPS 2024Entity Alignment with Noisy Annotations from Large Language Models
1039. NeurIPS 2024Evaluating alignment between humans and neural network representations in image-based learning tasks
1040. NeurIPS 2024Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
1041. NeurIPS 2024Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
1042. NeurIPS 2024Exploiting LLM Quantization
1043. NeurIPS 2024Exploring Adversarial Robustness of Deep State Space Models
1044. NeurIPS 2024Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
1045. NeurIPS 2024Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
1046. NeurIPS 2024Fast Best-of-N Decoding via Speculative Rejection
1047. NeurIPS 2024Fast yet Safe: Early-Exiting with Risk Control
1048. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
1049. NeurIPS 2024Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
1050. NeurIPS 2024FedGMark: Certifiably Robust Watermarking for Federated Graph 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。