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 473 篇，第 7 / 10 页
- ICLR 2025On the Adversarial Vulnerability of Label-Free Test-Time Adaptation
- ICLR 2025On the Hölder Stability of Multiset and Graph Neural Networks
- ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
- ICLR 2025On the Role of Attention Heads in Large Language Model Safety
- ICLR 2025On-the-fly Preference Alignment via Principle-Guided Decoding
- ICLR 2025One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment
- ICLR 2025Online Preference Alignment for Language Models via Count-based Exploration
- ICLR 2025Online-to-Offline RL for Agent Alignment
- ICLR 2025Pacmann: Efficient Private Approximate Nearest Neighbor Search
- ICLR 2025PAD: Personalized Alignment of LLMs at Decoding-time
- ICLR 2025Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning
- ICLR 2025PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment
- ICLR 2025PaLD: Detection of Text Partially Written by Large Language Models
- ICLR 2025Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
- ICLR 2025Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
- ICLR 2025Persistent Pre-training Poisoning of LLMs
- ICLR 2025Personality Alignment of Large Language Models
- ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
- ICLR 2025PFGuard: A Generative Framework with Privacy and Fairness Safeguards
- ICLR 2025PiCO: Peer Review in LLMs based on Consistency Optimization
- ICLR 2025Plastic Learning with Deep Fourier Features
- ICLR 2025Policy Design in Long-run Welfare Dynamics
- ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
- ICLR 2025Preference Diffusion for Recommendation
- ICLR 2025Preference Optimization for Reasoning with Pseudo Feedback
- ICLR 2025Privacy Auditing of Large Language Models
- ICLR 2025Privately Counting Partially Ordered Data
- ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
- ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
- ICLR 2025Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution
- ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
- ICLR 2025Programming Refusal with Conditional Activation Steering
- ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
- ICLR 2025ProtoSnap: Prototype Alignment For Cuneiform Signs
- ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
- ICLR 2025Provable weak-to-strong generalization via benign overfitting
- ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
- ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
- ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
- ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
- ICLR 2025QA-Calibration of Language Model Confidence Scores
- ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
- ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
- ICLR 2025Reassessing How to Compare and Improve the Calibration of Machine Learning Models
- ICLR 2025Reconciling Model Multiplicity for Downstream Decision Making
- ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
- ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
- ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
- ICLR 2025Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
- ICLR 2025Regretful Decisions under Label Noise
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。