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 41 / 92 页
- CVPR 2025Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
- CVPR 2025Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting
- CVPR 2025The Scene Language: Representing Scenes with Programs, Words, and Embeddings
- CVPR 2025Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning
- CVPR 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
- CVPR 2025Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting
- CVPR 2025Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
- CVPR 2025Towards Smart Point-and-Shoot Photography
- CVPR 2025Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
- CVPR 2025UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units
- CVPR 2025UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming
- CVPR 2025Unified Reconstruction of Static and Dynamic Scenes from Events
- CVPR 2025Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
- CVPR 2025VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models
- CVPR 2025VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
- CVPR 2025VinaBench: Benchmark for Faithful and Consistent Visual Narratives
- CVPR 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning
- ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
- ICLR 2025$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
- ICLR 20253D-Properties: Identifying Challenges in DPO and Charting a Path Forward
- ICLR 2025A Benchmark for Semantic Sensitive Information in LLMs Outputs
- ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
- ICLR 2025A Closer Look at Machine Unlearning for Large Language Models
- ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
- ICLR 2025A Generic Framework for Conformal Fairness
- ICLR 2025A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
- ICLR 2025A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
- ICLR 2025A Simple yet Effective $\Delta\Delta G$ Predictor is An Unsupervised Antibody Optimizer and Explainer
- ICLR 2025A Theoretical Framework for Partially-Observed Reward States in RLHF
- ICLR 2025A Transfer Attack to Image Watermarks
- ICLR 2025A transfer learning framework for weak to strong generalization
- ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
- ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
- ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
- ICLR 2025Adam-mini: Use Fewer Learning Rates To Gain More
- ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
- ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
- ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
- ICLR 2025Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
- ICLR 2025Advancing LLM Reasoning Generalists with Preference Trees
- ICLR 2025Advantage-Guided Distillation for Preference Alignment in Small Language Models
- ICLR 2025Adversarial Attacks on Data Attribution
- ICLR 2025Adversarial Latent Feature Augmentation for Fairness
- ICLR 2025Adversarial Machine Unlearning
- ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
- ICLR 2025Adversarial Search Engine Optimization for Large Language Models
- ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
- ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- ICLR 2025AI Sandbagging: Language Models can Strategically Underperform on Evaluations
- ICLR 2025AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
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。