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 125 篇，第 3 / 3 页

101. CVPR 2024SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency
102. CVPR 2024Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment
103. CVPR 2024SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling
104. CVPR 2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning
105. CVPR 2024Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
106. CVPR 2024Synergistic Global-space Camera and Human Reconstruction from Videos
107. CVPR 2024SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement
108. CVPR 2024Targeted Representation Alignment for Open-World Semi-Supervised Learning
109. CVPR 2024Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis
110. CVPR 2024Towards Accurate and Robust Architectures via Neural Architecture Search
111. CVPR 2024Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings
112. CVPR 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network
113. CVPR 2024TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light
114. CVPR 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets
115. CVPR 2024Unifying Automatic and Interactive Matting with Pretrained ViTs
116. CVPR 2024Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers
117. CVPR 2024Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
118. CVPR 2024Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
119. CVPR 2024Utility-Fairness Trade-Offs and How to Find Them
120. CVPR 2024VAREN: Very Accurate and Realistic Equine Network
121. CVPR 2024VideoCon: Robust Video-Language Alignment via Contrast Captions
122. CVPR 2024VidLA: Video-Language Alignment at Scale
123. CVPR 2024VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning
124. CVPR 2024Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection
125. CVPR 2024When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

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。