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 84 / 92 页
- CVPR 2023DiGA: Distil To Generalize and Then Adapt for Domain Adaptive Semantic Segmentation
- CVPR 2023DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction
- CVPR 2023DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling
- CVPR 2023DNF: Decouple and Feedback Network for Seeing in the Dark
- CVPR 2023Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis
- CVPR 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
- CVPR 2023EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
- CVPR 2023Efficient Map Sparsification Based on 2D and 3D Discretized Grids
- CVPR 2023EXCALIBUR: Encouraging and Evaluating Embodied Exploration
- CVPR 2023EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata
- CVPR 2023Exploring and Utilizing Pattern Imbalance
- CVPR 2023Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation
- CVPR 2023Feature Alignment and Uniformity for Test Time Adaptation
- CVPR 2023Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment
- CVPR 2023Frame Flexible Network
- CVPR 2023Frame-Event Alignment and Fusion Network for High Frame Rate Tracking
- CVPR 2023Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement
- CVPR 2023Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues
- CVPR 2023Generalist: Decoupling Natural and Robust Generalization
- CVPR 2023Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization
- CVPR 2023Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video
- CVPR 2023Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model
- CVPR 2023HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization
- CVPR 2023High-Res Facial Appearance Capture From Polarized Smartphone Images
- CVPR 2023How To Prevent the Continuous Damage of Noises To Model Training?
- CVPR 2023HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions
- CVPR 2023Human Body Shape Completion With Implicit Shape and Flow Learning
- CVPR 2023Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View
- CVPR 2023Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
- CVPR 2023Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling
- CVPR 2023Invertible Neural Skinning
- CVPR 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
- CVPR 2023Large-Capacity and Flexible Video Steganography via Invertible Neural Network
- CVPR 2023Learning Emotion Representations From Verbal and Nonverbal Communication
- CVPR 2023Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space
- CVPR 2023Learning To Zoom and Unzoom
- CVPR 2023MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision
- CVPR 2023MEGANE: Morphable Eyeglass and Avatar Network
- CVPR 2023NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation
- CVPR 2023NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations
- CVPR 2023On Calibrating Semantic Segmentation Models: Analyses and an Algorithm
- CVPR 2023On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation
- CVPR 2023On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering
- CVPR 2023OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation
- CVPR 2023Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
- CVPR 2023PACO: Parts and Attributes of Common Objects
- CVPR 2023Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words
- CVPR 2023Physically Adversarial Infrared Patches With Learnable Shapes and Locations
- CVPR 2023PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout
- CVPR 2023Prefix Conditioning Unifies Language and Label Supervision
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。