对齐与安全论文趋势 2023–2026
RLHF、偏好优化、红队与安全对齐
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 4,558 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 138 | 87 | 101 | 112 | 438 |
| 2024 | 348 | 156 | 246 | 125 | 875 |
| 2025 | 455 | 473 | 300 | 135 | 1,363 |
| 2026 | 480 | 623 | 551 | 228 | 1,882 |
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 4,558 篇，第 69 / 92 页
- ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
- ICLR 2024Confronting Reward Model Overoptimization with Constrained RLHF
- ICLR 2024Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
- ICLR 2024Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
- ICLR 2024Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
- ICLR 2024CPPO: Continual Learning for Reinforcement Learning with Human Feedback
- ICLR 2024Curiosity-driven Red-teaming for Large Language Models
- ICLR 2024Debiasing Attention Mechanism in Transformer without Demographics
- ICLR 2024Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
- ICLR 2024Defining and extracting generalizable interaction primitives from DNNs
- ICLR 2024Demonstration-Regularized RL
- ICLR 2024DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
- ICLR 2024Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
- ICLR 2024Detecting Pretraining Data from Large Language Models
- ICLR 2024Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
- ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
- ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
- ICLR 2024Effective and Efficient Federated Tree Learning on Hybrid Data
- ICLR 2024Enabling Lanuguage Models to Implicitly Learn Self-Improvement
- ICLR 2024Eureka: Human-Level Reward Design via Coding Large Language Models
- ICLR 2024Expressivity of ReLU-Networks under Convex Relaxations
- ICLR 2024f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
- ICLR 2024Fair and Efficient Contribution Valuation for Vertical Federated Learning
- ICLR 2024Faster Approximation of Probabilistic and Distributional Values via Least Squares
- ICLR 2024FedImpro: Measuring and Improving Client Update in Federated Learning
- ICLR 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
- ICLR 2024Few-Shot Detection of Machine-Generated Text using Style Representations
- ICLR 2024Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- ICLR 2024Fine-Tuning Language Models for Factuality
- ICLR 2024Finetuning Text-to-Image Diffusion Models for Fairness
- ICLR 2024FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
- ICLR 2024Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
- ICLR 2024Generative Judge for Evaluating Alignment
- ICLR 2024GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
- ICLR 2024Group Preference Optimization: Few-Shot Alignment of Large Language Models
- ICLR 2024How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
- ICLR 2024Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- ICLR 2024Implicit Neural Representations and the Algebra of Complex Wavelets
- ICLR 2024Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
- ICLR 2024Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
- ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
- ICLR 2024Language Model Decoding as Direct Metrics Optimization
- ICLR 2024Language Model Inversion
- ICLR 2024Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication
- ICLR 2024LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
- ICLR 2024Learning From Simplicial Data Based on Random Walks and 1D Convolutions
- ICLR 2024Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
- ICLR 2024Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
- ICLR 2024Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
- ICLR 2024LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查对齐与安全在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "alignment-and-safety"}
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。