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 22 / 27 页

1051. ICLR 2025TODO: Enhancing LLM Alignment with Ternary Preferences
1052. ICLR 2025Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
1053. ICLR 2025Towards a learning theory of representation alignment
1054. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
1055. ICLR 2025Towards counterfactual fairness through auxiliary variables
1056. ICLR 2025Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
1057. ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
1058. ICLR 2025Towards hyperparameter-free optimization with differential privacy
1059. ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
1060. ICLR 2025Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
1061. ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
1062. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
1063. ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
1064. ICLR 2025Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
1065. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
1066. ICLR 2025Training-Free Diffusion Model Alignment with Sampling Demons
1067. ICLR 2025Training-free LLM-generated Text Detection by Mining Token Probability Sequences
1068. ICLR 2025Transformers Learn Low Sensitivity Functions: Investigations and Implications
1069. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
1070. ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
1071. ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
1072. ICLR 2025Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
1073. ICLR 2025Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
1074. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
1075. ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
1076. ICLR 2025UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
1077. ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
1078. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
1079. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
1080. ICLR 2025Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
1081. ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
1082. ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
1083. ICLR 2025Variational Best-of-N Alignment
1084. ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
1085. ICLR 2025VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
1086. ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
1087. ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
1088. ICLR 2025Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
1089. ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
1090. ICLR 2025Wasserstein Distances, Neuronal Entanglement, and Sparsity
1091. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
1092. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
1093. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
1094. ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
1095. ICLR 2025Your Weak LLM is Secretly a Strong Teacher for Alignment
1096. ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
1097. ICLR 2024#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
1098. ICLR 2024A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
1099. ICLR 2024A unique M-pattern for micro-expression spotting in long videos
1100. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game

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。