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 1,363 篇，第 5 / 28 页
- ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
- ICLR 2025Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
- ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
- ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
- ICLR 2025Building Math Agents with Multi-Turn Iterative Preference Learning
- ICLR 2025Calibrating Expressions of Certainty
- ICLR 2025Can a Large Language Model be a Gaslighter?
- ICLR 2025Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
- ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
- ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
- ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
- ICLR 2025Can We Ignore Labels in Out of Distribution Detection?
- ICLR 2025Capturing the Temporal Dependence of Training Data Influence
- ICLR 2025Certified Robustness Under Bounded Levenshtein Distance
- ICLR 2025Certifying Counterfactual Bias in LLMs
- ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
- ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
- ICLR 2025CipherPrune: Efficient and Scalable Private Transformer Inference
- ICLR 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
- ICLR 2025Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
- ICLR 2025CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
- ICLR 2025Collapsed Language Models Promote Fairness
- ICLR 2025Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
- ICLR 2025Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
- ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
- ICLR 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration
- ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
- ICLR 2025Conformal Prediction Sets Can Cause Disparate Impact
- ICLR 2025Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
- ICLR 2025Conservative Contextual Bandits: Beyond Linear Representations
- ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
- ICLR 2025Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis
- ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
- ICLR 2025Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
- ICLR 2025Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization
- ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
- ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
- ICLR 2025Copyright-Protected Language Generation via Adaptive Model Fusion
- ICLR 2025Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
- ICLR 2025Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
- ICLR 2025CREAM: Consistency Regularized Self-Rewarding Language Models
- ICLR 2025Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
- ICLR 2025Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
- ICLR 2025DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
- ICLR 2025DarkBench: Benchmarking Dark Patterns in Large Language Models
- ICLR 2025Data Distillation for extrapolative protein design through exact preference optimization
- ICLR 2025Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
- ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
- ICLR 2025Dataset Ownership Verification in Contrastive Pre-trained Models
- ICLR 2025DCT-CryptoNets: Scaling Private Inference in the Frequency Domain
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。