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 1,882 篇，第 13 / 38 页
- ICLR 2026On Fairness of Task Arithmetic: The Role of Task Vectors
- ICLR 2026On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
- ICLR 2026On the Alignment Between Supervised and Self-Supervised Contrastive Learning
- ICLR 2026On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
- ICLR 2026On the Interaction of Compressibility and Adversarial Robustness
- ICLR 2026Only Brains Align with Brains: Cross-Region Patterns Expose Limits of Normative Models
- ICLR 2026OpenAgentSafety: A Comprehensive Framework For Evaluating Real-World AI Agent Safety
- ICLR 2026Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
- ICLR 2026OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
- ICLR 2026Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
- ICLR 2026Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
- ICLR 2026Optimizing Agent Planning for Security and Autonomy
- ICLR 2026Optimizing Canaries for Privacy Auditing with Metagradient Descent
- ICLR 2026Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement
- ICLR 2026ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation
- ICLR 2026OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
- ICLR 2026Out of the Shadows: Exploring a Latent Space for Neural Network Verification
- ICLR 2026Output Supervision Can Obfuscate the Chain of Thought
- ICLR 2026Oversmoothing, "Oversquashing'', Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
- ICLR 2026P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
- ICLR 2026P$^2$-DPO:Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
- ICLR 2026PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
- ICLR 2026PALC: Preference Alignment via Logit Calibration
- ICLR 2026PAMDP: Interact to Persona Alignment via a Partially Observable Markov Decision Process
- ICLR 2026Parameterized Hardness of Zonotope Containment and Neural Network Verification
- ICLR 2026PCPO: Proportionate Credit Policy Optimization for Preference Alignment of Image Generation Models
- ICLR 2026PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
- ICLR 2026Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
- ICLR 2026Persona Features Control Emergent Misalignment
- ICLR 2026Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It
- ICLR 2026PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
- ICLR 2026Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
- ICLR 2026Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants
- ICLR 2026PetaGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning
- ICLR 2026PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits
- ICLR 2026PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
- ICLR 2026Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
- ICLR 2026PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
- ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
- ICLR 2026PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
- ICLR 2026Polynomial, trigonometric, and tropical activations
- ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
- ICLR 2026PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
- ICLR 2026Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
- ICLR 2026Prediction with Expert Advice under Local Differential Privacy
- ICLR 2026Preference Leakage: A Contamination Problem in LLM-as-a-judge
- ICLR 2026Pretrain Value, Not Reward: Decoupled Value Policy Optimization
- ICLR 2026Pretrain–Test Task Alignment Governs Generalization in In-Context Learning
- ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
- ICLR 2026Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
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。