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 600 篇，第 1 / 12 页

1. CVPR 2026A Combination of Noise and Bilateral Filters Achieve Supralinear and
2. CVPR 2026ActivePolicy Active Gaussian Reconstruction and Optimization Strategy Based on Global-Local
3. CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and
4. CVPR 2026Adversarial Style Optimization Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers
5. CVPR 2026Aligning Multi-Character Narrative Image Generation with Multi-Aspect Human Preferences
6. CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
7. CVPR 2026All in One Unifying Deepfake Detection Tampering Localization and Source
8. CVPR 2026Anchoring the Mind of Multimodal Reasoners Cognitive Bias as a
9. CVPR 2026Ar2Can An Architect and an Artist Leveraging a Canvas for
10. CVPR 2026Avatar Forcing Real-Time Interactive Head Avatar Generation for Natural Conversation
11. CVPR 2026AviaSafe A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
12. CVPR 2026BackSplit The Importance of Sub-dividing the Background in Biomedical Lesion
13. CVPR 2026Batman Benign Knowledge Alignment Through Malicious Null Space in Federated
14. CVPR 2026Benchmarking Endoscopic Surgical Image Restoration and Beyond
15. CVPR 2026Beyond Duality A Hybrid Framework of Leveraging Shared and Private
16. CVPR 2026Beyond Euclidean Gossip KL-Barycentric Consensus on Heterogeneous and Imbalanced Images
17. CVPR 2026Beyond Matching to Tiles Bridging Unaligned Aerial and Satellite Views
18. CVPR 2026Beyond Myopic Alignment Lookahead Optimization for Online Class-Incremental Learning
19. CVPR 2026Beyond Sequential Tools A Unified VLM Agent System for Photographic
20. CVPR 2026Beyond Strict Pairing Arbitrarily Paired Training for High-Performance Infrared and
21. CVPR 2026Bias at the End of the Score
22. CVPR 2026BioVITA Biological Dataset Model and Benchmark for Visual-Textual-Acoustic Alignment
23. CVPR 2026Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning
24. CVPR 2026Boosting Visual Reprogramming for CLIP with Dual Granularity Alignment
25. CVPR 2026Bridging Domain Expertise and Generalization for Performance Estimation
26. CVPR 2026Bridging Pixels and Words Mask-Aware Local Semantic Fusion for Multimodal
27. CVPR 2026CATNet Collaborative Alignment and Transformation Network for Cooperative Perception
28. CVPR 2026CHEEM Continual Learning by Reuse New Adapt and Skip -
29. CVPR 2026Circular-DPO Aligning Multi-Stage 3D Generative Models via Preference Feedback Loop
30. CVPR 2026Clothe and Pose
31. CVPR 2026CoIn Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal
32. CVPR 2026ColorFLUX A Structure-Color Decoupling Framework for Old Photo Colorization
33. CVPR 2026Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
34. CVPR 2026Consensus vs. Controversy Mapping the Decision Space Where Architectures Diverge
35. CVPR 2026Copy-Transform-Paste Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints
36. CVPR 2026CoV-Align Efficient Fine-grained Cross-Modal Alignment with Cohesive Visual Semantics Priority
37. CVPR 2026CRAFT Aligning Diffusion Models with Fine-Tuning Is Easier Than You
38. CVPR 2026Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A
39. CVPR 2026Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark
40. CVPR 2026CUBic Coordinated Unified Bimanual Perception and Control Framework
41. CVPR 2026CVA Context-aware Video-text Alignment for Video Temporal Grounding
42. CVPR 2026D2-FOSA Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment
43. CVPR 2026DA-Mamba Learning Domain-Aware State Space Model for Global-Local Alignment in
44. CVPR 2026Decompose and Transfer CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action
45. CVPR 2026DeepProtect Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion
46. CVPR 2026Deformable Gaussian Occupancy Decoupling Rigid and Nonrigid Motion with Factorized
47. CVPR 2026Den-TP A Density-Balanced Data Curation and Evaluation Framework for Trajectory
48. CVPR 2026DETACH Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient
49. CVPR 2026Domain-Skewed Federated Learning with Feature Decoupling and Calibration
50. CVPR 2026Dr.Occ Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for

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。