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 1,363 篇，第 2 / 28 页

51. CVPR 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
52. CVPR 2025HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
53. CVPR 2025Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching
54. CVPR 2025HOT: Hadamard-based Optimized Training
55. CVPR 2025Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
56. CVPR 2025HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
57. CVPR 2025Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
58. CVPR 2025Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
59. CVPR 2025Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity
60. CVPR 2025Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning
61. CVPR 2025Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models
62. CVPR 2025InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
63. CVPR 2025iSegMan: Interactive Segment-and-Manipulate 3D Gaussians
64. CVPR 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learning
65. CVPR 2025JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems
66. CVPR 2025Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning
67. CVPR 2025LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation
68. CVPR 2025Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model
69. CVPR 2025Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References
70. CVPR 2025Let's Verify and Reinforce Image Generation Step by Step
71. CVPR 2025Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
72. CVPR 2025MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing
73. CVPR 2025MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos
74. CVPR 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
75. CVPR 2025MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data
76. CVPR 2025Monocular and Generalizable Gaussian Talking Head Animation
77. CVPR 2025MuTri: Multi-view Tri-alignment for OCT to OCTA 3D Image Translation
78. CVPR 2025Navigating Image Restoration with VAR's Distribution Alignment Prior
79. CVPR 2025No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather
80. CVPR 2025ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry Staining
81. CVPR 2025PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
82. CVPR 2025PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation
83. CVPR 2025PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
84. CVPR 2025Personalized Preference Fine-tuning of Diffusion Models
85. CVPR 2025PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution
86. CVPR 2025Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
87. CVPR 2025PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes
88. CVPR 2025Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy
89. CVPR 2025PLeaS - Merging Models with Permutations and Least Squares
90. CVPR 2025Plug-and-Play Versatile Compressed Video Enhancement
91. CVPR 2025POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
92. CVPR 2025Practical Solutions to the Relative Pose of Three Calibrated Cameras
93. CVPR 2025Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance
94. CVPR 2025PrEditor3D: Fast and Precise 3D Shape Editing
95. CVPR 2025Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
96. CVPR 2025Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content
97. CVPR 2025QuCOOP: A Versatile Framework for Solving Composite and Binary-Parametrised Problems on Quantum Annealers
98. CVPR 2025ReNeg: Learning Negative Embedding with Reward Guidance
99. CVPR 2025Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation
100. CVPR 2025Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection

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。