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 1,339 篇，第 16 / 27 页

751. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
752. ICLR 2025Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
753. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
754. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
755. ICLR 2025Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
756. ICLR 2025DSPO: Direct Score Preference Optimization for Diffusion Model Alignment
757. ICLR 2025Durable Quantization Conditioned Misalignment Attack on Large Language Models
758. ICLR 2025DynAlign: Unsupervised Dynamic Taxonomy Alignment for Cross-Domain Segmentation
759. ICLR 2025Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
760. ICLR 2025DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
761. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
762. ICLR 2025Effective Interplay between Sparsity and Quantization: From Theory to Practice
763. ICLR 2025Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based Coresets
764. ICLR 2025Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
765. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
766. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
767. ICLR 2025EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
768. ICLR 2025Encryption-Friendly LLM Architecture
769. ICLR 2025Endless Jailbreaks with Bijection Learning
770. ICLR 2025Endowing Visual Reprogramming with Adversarial Robustness
771. ICLR 2025Energy-based Backdoor Defense Against Federated Graph Learning
772. ICLR 2025Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary
773. ICLR 2025Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies
774. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
775. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
776. ICLR 2025Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer
777. ICLR 2025ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
778. ICLR 2025EvA: Erasing Spurious Correlations with Activations
779. ICLR 2025Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
780. ICLR 2025Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes
781. ICLR 2025Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm
782. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
783. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
784. ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
785. ICLR 2025Fair Clustering in the Sliding Window Model
786. ICLR 2025FairDen: Fair Density-Based Clustering
787. ICLR 2025FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
788. ICLR 2025Fantastic Copyrighted Beasts and How (Not) to Generate Them
789. ICLR 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
790. ICLR 2025Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
791. ICLR 2025Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
792. ICLR 2025Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
793. ICLR 2025FormalAlign: Automated Alignment Evaluation for Autoformalization
794. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
795. ICLR 2025From Search to Sampling: Generative Models for Robust Algorithmic Recourse
796. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
797. ICLR 2025Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation
798. ICLR 2025GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
799. ICLR 2025Generalization and Distributed Learning of GFlowNets
800. ICLR 2025Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

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。