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 875 篇，第 17 / 18 页

801. NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
802. NeurIPS 2024Sequential Harmful Shift Detection Without Labels
803. NeurIPS 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
804. NeurIPS 2024SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
805. NeurIPS 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
806. NeurIPS 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
807. NeurIPS 2024SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
808. NeurIPS 2024SimPO: Simple Preference Optimization with a Reference-Free Reward
809. NeurIPS 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
810. NeurIPS 2024Soft-Label Integration for Robust Toxicity Classification
811. NeurIPS 2024Spectral Editing of Activations for Large Language Model Alignment
812. NeurIPS 2024SpeechAlign: Aligning Speech Generation to Human Preferences
813. NeurIPS 2024SSDM: Scalable Speech Dysfluency Modeling
814. NeurIPS 2024Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
815. NeurIPS 2024Stepwise Alignment for Constrained Language Model Policy Optimization
816. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
817. NeurIPS 2024Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
818. NeurIPS 2024T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
819. NeurIPS 2024Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
820. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
821. NeurIPS 2024Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
822. NeurIPS 2024Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
823. NeurIPS 2024TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
824. NeurIPS 2024The Art of Saying No: Contextual Noncompliance in Language Models
825. NeurIPS 2024The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
826. NeurIPS 2024The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
827. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
828. NeurIPS 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
829. NeurIPS 2024TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
830. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
831. NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
832. NeurIPS 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
833. NeurIPS 2024Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
834. NeurIPS 2024Transfer Q-star : Principled Decoding for LLM Alignment
835. NeurIPS 2024Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
836. NeurIPS 2024Transferable Adversarial Attacks on SAM and Its Downstream Models
837. NeurIPS 2024Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
838. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
839. NeurIPS 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
840. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
841. NeurIPS 2024UltraMedical: Building Specialized Generalists in Biomedicine
842. NeurIPS 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vector
843. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
844. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
845. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
846. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
847. NeurIPS 2024Unified Lexical Representation for Interpretable Visual-Language Alignment
848. NeurIPS 2024UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
849. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
850. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

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。