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 135 篇，第 3 / 3 页

101. CVPR 2025Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment
102. CVPR 2025Rethinking Reconstruction and Denoising in the Dark: New Perspective, General Architecture and Beyond
103. CVPR 2025RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety
104. CVPR 2025Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment
105. CVPR 2025Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On
106. CVPR 2025RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
107. CVPR 2025SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
108. CVPR 2025SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
109. CVPR 2025Shape and Texture: What Influences Reliable Optical Flow Estimation?
110. CVPR 2025Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models
111. CVPR 2025SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
112. CVPR 2025SLVR: Super-Light Visual Reconstruction via Blueprint Controllable Convolutions and Exploring Feature Diversity Representation
113. CVPR 2025SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization
114. CVPR 2025SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models
115. CVPR 2025SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization
116. CVPR 2025STINR: Deciphering Spatial Transcriptomics via Implicit Neural Representation
117. CVPR 2025Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning
118. CVPR 2025SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
119. CVPR 2025Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
120. CVPR 2025Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting
121. CVPR 2025The Scene Language: Representing Scenes with Programs, Words, and Embeddings
122. CVPR 2025Towards Cost-Effective Learning: A Synergy of Semi-Supervised and Active Learning
123. CVPR 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
124. CVPR 2025Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting
125. CVPR 2025Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
126. CVPR 2025Towards Smart Point-and-Shoot Photography
127. CVPR 2025Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
128. CVPR 2025UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units
129. CVPR 2025UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming
130. CVPR 2025Unified Reconstruction of Static and Dynamic Scenes from Events
131. CVPR 2025Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
132. CVPR 2025VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models
133. CVPR 2025VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
134. CVPR 2025VinaBench: Benchmark for Faithful and Consistent Visual Narratives
135. CVPR 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning

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。