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 1,363 篇，第 21 / 28 页

1001. NeurIPS 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
1002. NeurIPS 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
1003. NeurIPS 2025CPO: Condition Preference Optimization for Controllable Image Generation
1004. NeurIPS 2025CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
1005. NeurIPS 2025CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
1006. NeurIPS 2025CVGL: Causal Learning and Geometric Topology
1007. NeurIPS 2025DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
1008. NeurIPS 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
1009. NeurIPS 2025Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences
1010. NeurIPS 2025DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
1011. NeurIPS 2025Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
1012. NeurIPS 2025DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
1013. NeurIPS 2025Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
1014. NeurIPS 2025Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
1015. NeurIPS 2025Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
1016. NeurIPS 2025Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
1017. NeurIPS 2025Dimensional Collapse in VQVAEs: Evidence and Remedies
1018. NeurIPS 2025Dimensionality Mismatch Between Brains and Artificial Neural Networks
1019. NeurIPS 2025Direct Alignment with Heterogeneous Preferences
1020. NeurIPS 2025Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models
1021. NeurIPS 2025Distillation Robustifies Unlearning
1022. NeurIPS 2025Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
1023. NeurIPS 2025Distributional LLM-as-a-Judge
1024. NeurIPS 2025Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
1025. NeurIPS 2025DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
1026. NeurIPS 2025Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
1027. NeurIPS 2025Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
1028. NeurIPS 2025Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models
1029. NeurIPS 2025Doubly Robust Alignment for Large Language Models
1030. NeurIPS 2025DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
1031. NeurIPS 2025DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
1032. NeurIPS 2025DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
1033. NeurIPS 2025Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
1034. NeurIPS 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
1035. NeurIPS 2025DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
1036. NeurIPS 2025Dynamic Diameter in High-Dimensions against Adaptive Adversary and Beyond
1037. NeurIPS 2025Dynamic Risk Assessments for Offensive Cybersecurity Agents
1038. NeurIPS 2025Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
1039. NeurIPS 2025Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
1040. NeurIPS 2025Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
1041. NeurIPS 2025Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design
1042. NeurIPS 2025Elastic Robust Unlearning of Specific Knowledge in Large Language Models
1043. NeurIPS 2025ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
1044. NeurIPS 2025Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
1045. NeurIPS 2025Enhancing CLIP Robustness via Cross-Modality Alignment
1046. NeurIPS 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
1047. NeurIPS 2025Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
1048. NeurIPS 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
1049. NeurIPS 2025Erasing Conceptual Knowledge from Language Models
1050. NeurIPS 2025Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism

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。