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 1 / 28 页

1. CVPR 20254DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians
2. CVPR 2025Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
3. CVPR 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models
4. CVPR 2025AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
5. CVPR 2025Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
6. CVPR 2025AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer
7. CVPR 2025Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
8. CVPR 2025Any6D: Model-free 6D Pose Estimation of Novel Objects
9. CVPR 2025AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
10. CVPR 2025ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
11. CVPR 2025Asynchronous Collaborative Graph Representation for Frames and Events
12. CVPR 2025Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
13. CVPR 2025Automatic Spectral Calibration of Hyperspectral Images: Method, Dataset and Benchmark
14. CVPR 2025Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
15. CVPR 2025BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment
16. CVPR 2025Boost Your Human Image Generation Model via Direct Preference Optimization
17. CVPR 2025Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport
18. CVPR 2025Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow
19. CVPR 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
20. CVPR 2025Calibrated Multi-Preference Optimization for Aligning Diffusion Models
21. CVPR 2025Camera Resection from Known Line Pencils and a Radially Distorted Scanline
22. CVPR 2025Camouflage Anything: Learning to Hide using Controlled Out-painting and Representation Engineering
23. CVPR 2025Can Text-to-Video Generation help Video-Language Alignment?
24. CVPR 2025CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
25. CVPR 2025Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment
26. CVPR 2025Chebyshev Attention Depth Permutation Texture Network with Latent Texture Attribute Loss
27. CVPR 2025ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
28. CVPR 2025Continual SFT Matches Multimodal RLHF with Negative Supervision
29. CVPR 2025Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
30. CVPR 2025CrossOver: 3D Scene Cross-Modal Alignment
31. CVPR 2025Curriculum Direct Preference Optimization for Diffusion and Consistency Models
32. CVPR 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
33. CVPR 2025Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
34. CVPR 2025Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
35. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
36. CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
37. CVPR 2025Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality
38. CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
39. CVPR 2025Doppelgangers and Adversarial Vulnerability
40. CVPR 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
41. CVPR 2025EBS-EKF: Accurate and High Frequency Event-based Star Tracking
42. CVPR 2025EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
43. CVPR 2025Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework
44. CVPR 2025Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation
45. CVPR 2025Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces
46. CVPR 2025EventPSR: Surface Normal and Reflectance Estimation from Photometric Stereo Using an Event Camera
47. CVPR 2025Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
48. CVPR 2025Flexible Group Count Enables Hassle-Free Structured Pruning
49. CVPR 2025Font-Agent: Enhancing Font Understanding with Large Language Models
50. CVPR 2025Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution

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。