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 56 / 92 页
- ICML 2025Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
- ICML 2025TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization
- ICML 2025Test-time Correlation Alignment
- ICML 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
- ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
- ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
- ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
- ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
- ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
- ICML 2025The Limits of Predicting Agents from Behaviour
- ICML 2025The Lock-in Hypothesis: Stagnation by Algorithm
- ICML 2025The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
- ICML 2025The Missing Alignment Link of In-context Learning on Sequences
- ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
- ICML 2025The Relationship Between No-Regret Learning and Online Conformal Prediction
- ICML 2025Theoretical guarantees on the best-of-n alignment policy
- ICML 2025Thinking LLMs: General Instruction Following with Thought Generation
- ICML 2025TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
- ICML 2025Tokenized Bandit for LLM Decoding and Alignment
- ICML 2025Topological Signatures of Adversaries in Multimodal Alignments
- ICML 2025Towards an Explainable Comparison and Alignment of Feature Embeddings
- ICML 2025Towards Cost-Effective Reward Guided Text Generation
- ICML 2025Towards Memorization Estimation: Fast, Formal and Free
- ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
- ICML 2025Training Deep Learning Models with Norm-Constrained LMOs
- ICML 2025Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
- ICML 2025Transformative or Conservative? Conservation laws for ResNets and Transformers
- ICML 2025TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
- ICML 2025TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
- ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
- ICML 2025Unconstrained Robust Online Convex Optimization
- ICML 2025Understanding High-Dimensional Bayesian Optimization
- ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
- ICML 2025Understanding the Emergence of Multimodal Representation Alignment
- ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
- ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
- ICML 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
- ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
- ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
- ICML 2025When, Where and Why to Average Weights?
- NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
- NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
- NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
- NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
- NeurIPS 2025A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
- NeurIPS 2025A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity
- NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
- NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
- NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
- NeurIPS 2025AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
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。