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 348 篇，第 1 / 7 页

1. NeurIPS 2024$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
2. NeurIPS 20243D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
3. NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
4. NeurIPS 2024A Novel Benchmark for Decision-Making in Uncertain and Competitive Games
5. NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
6. NeurIPS 2024A teacher-teacher framework for clinical language representation learning
7. NeurIPS 2024A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
8. NeurIPS 2024A Theoretical Understanding of Self-Correction through In-context Alignment
9. NeurIPS 2024Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
10. NeurIPS 2024Achieving Domain-Independent Certified Robustness via Knowledge Continuity
11. NeurIPS 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
12. NeurIPS 2024Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
13. NeurIPS 2024Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
14. NeurIPS 2024Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
15. NeurIPS 2024Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
16. NeurIPS 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
17. NeurIPS 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detection
18. NeurIPS 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
19. NeurIPS 2024Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
20. NeurIPS 2024Aligner: Efficient Alignment by Learning to Correct
21. NeurIPS 2024Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
22. NeurIPS 2024Aligning Large Language Models with Representation Editing: A Control Perspective
23. NeurIPS 2024Aligning Model Properties via Conformal Risk Control
24. NeurIPS 2024Aligning to Thousands of Preferences via System Message Generalization
25. NeurIPS 2024Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
26. NeurIPS 2024Alignment for Honesty
27. NeurIPS 2024Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
28. NeurIPS 2024ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
29. NeurIPS 2024Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
30. NeurIPS 2024Axioms for AI Alignment from Human Feedback
31. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
32. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
33. NeurIPS 2024Bayesian-guided Label Mapping for Visual Reprogramming
34. NeurIPS 2024Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
35. NeurIPS 2024Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
36. NeurIPS 2024Beyond Slow Signs in High-fidelity Model Extraction
37. NeurIPS 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
38. NeurIPS 2024Biomedical Visual Instruction Tuning with Clinician Preference Alignment
39. NeurIPS 2024BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
40. NeurIPS 2024Boosting the Potential of Large Language Models with an Intelligent Information Assistant
41. NeurIPS 2024Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning
42. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
43. NeurIPS 2024Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
44. NeurIPS 2024Calibrated Self-Rewarding Vision Language Models
45. NeurIPS 2024Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
46. NeurIPS 2024Can Large Language Model Agents Simulate Human Trust Behavior?
47. NeurIPS 2024Can Models Learn Skill Composition from Examples?
48. NeurIPS 2024Can Simple Averaging Defeat Modern Watermarks?
49. NeurIPS 2024Can Transformers Smell Like Humans?
50. NeurIPS 2024Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification

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。