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 50 / 92 页
- ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
- ICLR 2025Towards hyperparameter-free optimization with differential privacy
- ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
- ICLR 2025Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
- ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
- ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
- ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
- ICLR 2025Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
- ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
- ICLR 2025Training-Free Diffusion Model Alignment with Sampling Demons
- ICLR 2025Training-free LLM-generated Text Detection by Mining Token Probability Sequences
- ICLR 2025Transformers Learn Low Sensitivity Functions: Investigations and Implications
- ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
- ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
- ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
- ICLR 2025Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
- ICLR 2025Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
- ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
- ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
- ICLR 2025UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
- ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
- ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
- ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
- ICLR 2025Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
- ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
- ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
- ICLR 2025Variational Best-of-N Alignment
- ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
- ICLR 2025VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
- ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
- ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
- ICLR 2025Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
- ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
- ICLR 2025Wasserstein Distances, Neuronal Entanglement, and Sparsity
- ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
- ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
- ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
- ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
- ICLR 2025Your Weak LLM is Secretly a Strong Teacher for Alignment
- ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
- ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
- ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
- ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
- ICML 2025A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
- ICML 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
- ICML 2025A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
- ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
- ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
- ICML 2025Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
- ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
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。