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 22 / 29 页

1051. NeurIPS 2024FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
1052. NeurIPS 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
1053. NeurIPS 2024Few-Shot Adversarial Prompt Learning on Vision-Language Models
1054. NeurIPS 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning
1055. NeurIPS 2024FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
1056. NeurIPS 2024FLAME : Factuality-Aware Alignment for Large Language Models
1057. NeurIPS 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
1058. NeurIPS 2024From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
1059. NeurIPS 2024From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
1060. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
1061. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
1062. NeurIPS 2024Generalizable Person Re-identification via Balancing Alignment and Uniformity
1063. NeurIPS 2024Geometric-Averaged Preference Optimization for Soft Preference Labels
1064. NeurIPS 2024Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
1065. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
1066. NeurIPS 2024GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
1067. NeurIPS 2024Group Robust Preference Optimization in Reward-free RLHF
1068. NeurIPS 2024Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
1069. NeurIPS 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
1070. NeurIPS 2024HelpSteer 2: Open-source dataset for training top-performing reward models
1071. NeurIPS 2024HonestLLM: Toward an Honest and Helpful Large Language Model
1072. NeurIPS 2024Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
1073. NeurIPS 2024HuRef: HUman-REadable Fingerprint for Large Language Models
1074. NeurIPS 2024Imitating Language via Scalable Inverse Reinforcement Learning
1075. NeurIPS 2024Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
1076. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
1077. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
1078. NeurIPS 2024Improving Alignment and Robustness with Circuit Breakers
1079. NeurIPS 2024Improving Context-Aware Preference Modeling for Language Models
1080. NeurIPS 2024Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
1081. NeurIPS 2024Improving Subgroup Robustness via Data Selection
1082. NeurIPS 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
1083. NeurIPS 2024InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
1084. NeurIPS 2024Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
1085. NeurIPS 2024Interpreting Learned Feedback Patterns in Large Language Models
1086. NeurIPS 2024Invisible Image Watermarks Are Provably Removable Using Generative AI
1087. NeurIPS 2024Iterative Reasoning Preference Optimization
1088. NeurIPS 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
1089. NeurIPS 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
1090. NeurIPS 2024Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
1091. NeurIPS 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
1092. NeurIPS 2024Kernel PCA for Out-of-Distribution Detection
1093. NeurIPS 2024Label Alignment Regularization for Distribution Shift
1094. NeurIPS 2024LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
1095. NeurIPS 2024LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
1096. NeurIPS 2024Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
1097. NeurIPS 2024Large Language Model Unlearning
1098. NeurIPS 2024Large Language Model Unlearning via Embedding-Corrupted Prompts
1099. NeurIPS 2024Large language model validity via enhanced conformal prediction methods
1100. NeurIPS 2024Latent Functional Maps: a spectral framework for representation alignment

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。