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 74 / 92 页
- ICML 2024Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
- ICML 2024MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation
- ICML 2024Model Alignment as Prospect Theoretic Optimization
- ICML 2024Model Assessment and Selection under Temporal Distribution Shift
- ICML 2024Momentum Particle Maximum Likelihood
- ICML 2024Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks
- ICML 2024Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy
- ICML 2024MusicRL: Aligning Music Generation to Human Preferences
- ICML 2024Naive Bayes Classifiers over Missing Data: Decision and Poisoning
- ICML 2024Nash Learning from Human Feedback
- ICML 2024Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
- ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
- ICML 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF
- ICML 2024On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
- ICML 2024On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
- ICML 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Training
- ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
- ICML 2024Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
- ICML 2024Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
- ICML 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
- ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
- ICML 2024OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
- ICML 2024Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors
- ICML 2024Pairwise Alignment Improves Graph Domain Adaptation
- ICML 2024PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition
- ICML 2024PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
- ICML 2024Perfect Alignment May be Poisonous to Graph Contrastive Learning
- ICML 2024Perturb-and-Project: Differentially Private Similarities and Marginals
- ICML 2024Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach
- ICML 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
- ICML 2024Position: A Roadmap to Pluralistic Alignment
- ICML 2024Position: A Safe Harbor for AI Evaluation and Red Teaming
- ICML 2024Position: Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis
- ICML 2024Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation
- ICML 2024Position: Explain to Question not to Justify
- ICML 2024Position: Intent-aligned AI Systems Must Optimize for Agency Preservation
- ICML 2024Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI
- ICML 2024Position: Technical Research and Talent is Needed for Effective AI Governance
- ICML 2024Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
- ICML 2024Position: Towards Unified Alignment Between Agents, Humans, and Environment
- ICML 2024Position: TrustLLM: Trustworthiness in Large Language Models
- ICML 2024Positive and Unlabeled Learning with Controlled Probability Boundary Fence
- ICML 2024Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models
- ICML 2024Pricing with Contextual Elasticity and Heteroscedastic Valuation
- ICML 2024Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
- ICML 2024Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
- ICML 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
- ICML 2024Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource Allocation
- ICML 2024Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- ICML 2024Provably Robust DPO: Aligning Language Models with Noisy Feedback
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。