对齐与安全论文趋势 2023–2026

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。

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 112 篇，第 2 / 3 页

51. CVPR 2023Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video
52. CVPR 2023Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model
53. CVPR 2023HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization
54. CVPR 2023High-Res Facial Appearance Capture From Polarized Smartphone Images
55. CVPR 2023How To Prevent the Continuous Damage of Noises To Model Training?
56. CVPR 2023HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions
57. CVPR 2023Human Body Shape Completion With Implicit Shape and Flow Learning
58. CVPR 2023Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View
59. CVPR 2023Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
60. CVPR 2023Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling
61. CVPR 2023Invertible Neural Skinning
62. CVPR 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
63. CVPR 2023Large-Capacity and Flexible Video Steganography via Invertible Neural Network
64. CVPR 2023Learning Emotion Representations From Verbal and Nonverbal Communication
65. CVPR 2023Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space
66. CVPR 2023Learning To Zoom and Unzoom
67. CVPR 2023MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision
68. CVPR 2023MEGANE: Morphable Eyeglass and Avatar Network
69. CVPR 2023NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation
70. CVPR 2023NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations
71. CVPR 2023On Calibrating Semantic Segmentation Models: Analyses and an Algorithm
72. CVPR 2023On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation
73. CVPR 2023On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering
74. CVPR 2023OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation
75. CVPR 2023Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
76. CVPR 2023PACO: Parts and Attributes of Common Objects
77. CVPR 2023Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words
78. CVPR 2023Physically Adversarial Infrared Patches With Learnable Shapes and Locations
79. CVPR 2023PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout
80. CVPR 2023Prefix Conditioning Unifies Language and Label Supervision
81. CVPR 2023Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation
82. CVPR 2023PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment
83. CVPR 2023Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation
84. CVPR 2023Re-Basin via Implicit Sinkhorn Differentiation
85. CVPR 2023Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives
86. CVPR 2023Reliable and Interpretable Personalized Federated Learning
87. CVPR 2023Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment
88. CVPR 2023Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution
89. CVPR 2023Revisiting Rotation Averaging: Uncertainties and Robust Losses
90. CVPR 2023RiDDLE: Reversible and Diversified De-Identification With Latent Encryptor
91. CVPR 2023SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
92. CVPR 2023Scalable, Detailed and Mask-Free Universal Photometric Stereo
93. CVPR 2023SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text
94. CVPR 2023SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
95. CVPR 2023Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation
96. CVPR 2023ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency
97. CVPR 2023SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization
98. CVPR 2023StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator
99. CVPR 2023SunStage: Portrait Reconstruction and Relighting Using the Sun as a Light Stage
100. CVPR 2023Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models

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。