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 73 / 92 页
- ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
- ICML 2024FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
- ICML 2024FESSNC: Fast Exponentially Stable and Safe Neural Controller
- ICML 2024Flextron: Many-in-One Flexible Large Language Model
- ICML 2024From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
- ICML 2024Fundamental Limitations of Alignment in Large Language Models
- ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
- ICML 2024GNNs Also Deserve Editing, and They Need It More Than Once
- ICML 2024Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
- ICML 2024GRATH: Gradual Self-Truthifying for Large Language Models
- ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
- ICML 2024High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost
- ICML 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
- ICML 2024How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
- ICML 2024How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
- ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
- ICML 2024IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
- ICML 2024Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
- ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
- ICML 2024Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
- ICML 2024Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
- ICML 2024In-Context Language Learning: Architectures and Algorithms
- ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
- ICML 2024InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
- ICML 2024Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification
- ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
- ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
- ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
- ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
- ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs
- ICML 2024KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
- ICML 2024Language Models Represent Beliefs of Self and Others
- ICML 2024LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
- ICML 2024Learning and Forgetting Unsafe Examples in Large Language Models
- ICML 2024Learning Associative Memories with Gradient Descent
- ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse
- ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
- ICML 2024Learning Linear Block Error Correction Codes
- ICML 2024Learning Modality Knowledge Alignment for Cross-Modality Transfer
- ICML 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
- ICML 2024Learning to Remove Cuts in Integer Linear Programming
- ICML 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)
- ICML 2024Limited Preference Aided Imitation Learning from Imperfect Demonstrations
- ICML 2024Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
- ICML 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
- ICML 2024Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
- ICML 2024MaxMin-RLHF: Alignment with Diverse Human Preferences
- ICML 2024Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization
- ICML 2024MGit: A Model Versioning and Management System
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。