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 300 篇，第 5 / 6 页
- ICML 2025Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
- ICML 2025Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
- ICML 2025Position: The Right to AI
- ICML 2025Position: We Need Responsible, Application-Driven (RAD) AI Research
- ICML 2025Positional Attention: Expressivity and Learnability of Algorithmic Computation
- ICML 2025Preference Learning for AI Alignment: a Causal Perspective
- ICML 2025Preference learning made easy: Everything should be understood through win rate
- ICML 2025Preference Optimization for Combinatorial Optimization Problems
- ICML 2025Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
- ICML 2025Private Federated Learning using Preference-Optimized Synthetic Data
- ICML 2025Progressively Label Enhancement for Large Language Model Alignment
- ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
- ICML 2025ProSec: Fortifying Code LLMs with Proactive Security Alignment
- ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
- ICML 2025Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
- ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
- ICML 2025R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
- ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
- ICML 2025RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
- ICML 2025Reducing Tool Hallucination via Reliability Alignment
- ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
- ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
- ICML 2025Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
- ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
- ICML 2025Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
- ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
- ICML 2025Risk and cross validation in ridge regression with correlated samples
- ICML 2025RLTHF: Targeted Human Feedback for LLM Alignment
- ICML 2025ROPO: Robust Preference Optimization for Large Language Models
- ICML 2025RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
- ICML 2025RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
- ICML 2025SAE-V: Interpreting Multimodal Models for Enhanced Alignment
- ICML 2025Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
- ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
- ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
- ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
- ICML 2025Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
- ICML 2025Safety Reasoning with Guidelines
- ICML 2025Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
- ICML 2025Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
- ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
- ICML 2025Self-Consistency Preference Optimization
- ICML 2025Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
- ICML 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
- ICML 2025SEMU: Singular Value Decomposition for Efficient Machine Unlearning
- ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
- ICML 2025SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
- ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
- ICML 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
- ICML 2025Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
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。