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 1,882 篇，第 5 / 38 页
- CVPR 2026Towards Fine-Grained Attribution Instance-Aware Preference Optimization for Aligning Diffusion Models
- CVPR 2026Towards Unified Human Perception and Machine Understanding Token Flow Guided
- CVPR 2026TreeTeaming Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
- CVPR 2026TROPHIES Temporal Reconstruction of Places Humans and Cameras from Multi-view
- CVPR 2026TWEO Transformers Without Extreme Outliers Enables FP8 Training And Quantization
- CVPR 2026UFO Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene
- CVPR 2026Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
- CVPR 2026Understanding and Enforcing Weight Disentanglement in Task Arithmetic
- CVPR 2026Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled
- CVPR 2026UniFusion A Unified Image Fusion Framework with Robust Representation and
- CVPR 2026Unstitching the Chimera Frame-Level Risk and Train-Free Mitigation for Video
- CVPR 2026VA-p Variational Policy Alignment for Pixel-Aware Autoregressive Generation
- CVPR 2026VDE Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and
- CVPR 2026VGA Empowering Aerial-Ground Localization by Visual Geometry Alignment
- CVPR 2026VIAFormer Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement
- CVPR 2026View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
- CVPR 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery
- CVPR 2026Voxify3D Pixel Art Meets Volumetric Rendering
- CVPR 2026VRCLIP Multimodal Canonical Correlation Alignment for CLIP-Driven Vision-Radio Person Re-Identification
- CVPR 2026VT-Intrinsic Physics-Based Decomposition of Reflectance and Shading using a Single
- CVPR 2026What Do Visual Tokens Really Encode Uncovering Sparsity and Redundancy
- CVPR 2026What Is It Like to Be a Noise An Entropy-based
- CVPR 2026What Is the Optimal Ranking Score Between Precision and Recall
- CVPR 2026When Understanding Becomes a Risk Authenticity and Safety Risks in
- CVPR 2026Where MLLMs Attend and What They Rely On Explaining Autoregressive
- CVPR 2026WHU-MARS A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identification
- CVPR 2026WildCap Facial Albedo Capture in the Wild via Hybrid Inverse
- CVPR 2026Zero-shot Detection of AI-Generated Image via RAW-RGB Alignment
- ICLR 2026(Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Privacy Assessment for LLMs
- ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
- ICLR 2026A Fair Bayesian Inference through Matched Gibbs Posterior
- ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
- ICLR 2026A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
- ICLR 2026A Unified Total Variation Framework for Membrane Potential Perturbation Dynamic
- ICLR 2026A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
- ICLR 2026Activation Steering for LLM Alignment via a Unified ODE-Based Framework
- ICLR 2026Activation Steering with a Feedback Controller
- ICLR 2026ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
- ICLR 2026AdAEM: An Adaptively and Automated Extensible Evaluation Method of LLMs' Value Difference
- ICLR 2026Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
- ICLR 2026Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
- ICLR 2026Adaptive Social Learning via Mode Policy Optimization for Language Agents
- ICLR 2026AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
- ICLR 2026AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
- ICLR 2026Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
- ICLR 2026Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
- ICLR 2026Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
- ICLR 2026Align-SAM: Seeking Flatter Minima for Better Cross-Subset Alignment
- ICLR 2026Aligner, Diagnose Thyself: A Meta-Learning Paradigm for Fusing Intrinsic Feedback in Preference Alignment
- ICLR 2026Aligning Collaborative View Recovery and Tensorial Subspace Learning via Latent Representation for Incomplete Multi-View Clustering
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。