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 4,558 篇，第 81 / 92 页

4001. NeurIPS 2024Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
4002. NeurIPS 2024Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
4003. NeurIPS 2024Query-Based Adversarial Prompt Generation
4004. NeurIPS 2024RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
4005. NeurIPS 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
4006. NeurIPS 2024RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
4007. NeurIPS 2024Rapid Plug-in Defenders
4008. NeurIPS 2024RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
4009. NeurIPS 2024Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
4010. NeurIPS 2024RedCode: Multi-dimensional Safety Benchmark for Code Agents
4011. NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
4012. NeurIPS 2024Refusal in Language Models Is Mediated by a Single Direction
4013. NeurIPS 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
4014. NeurIPS 2024Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
4015. NeurIPS 2024Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
4016. NeurIPS 2024Relational Verification Leaps Forward with RABBit
4017. NeurIPS 2024ReMoDetect: Reward Models Recognize Aligned LLM's Generations
4018. NeurIPS 2024Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
4019. NeurIPS 2024Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
4020. NeurIPS 2024Rethinking LLM Memorization through the Lens of Adversarial Compression
4021. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
4022. NeurIPS 2024Revisiting Few-Shot Object Detection with Vision-Language Models
4023. NeurIPS 2024Risk-Averse Fine-tuning of Large Language Models
4024. NeurIPS 2024Robust Conformal Prediction Using Privileged Information
4025. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
4026. NeurIPS 2024Robust Reinforcement Learning from Corrupted Human Feedback
4027. NeurIPS 2024RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
4028. NeurIPS 2024Rule Based Rewards for Language Model Safety
4029. NeurIPS 2024Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
4030. NeurIPS 2024SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
4031. NeurIPS 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
4032. NeurIPS 2024SafeWorld: Geo-Diverse Safety Alignment
4033. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
4034. NeurIPS 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
4035. NeurIPS 2024Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
4036. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
4037. NeurIPS 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
4038. NeurIPS 2024Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
4039. NeurIPS 2024SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
4040. NeurIPS 2024Selective Generation for Controllable Language Models
4041. NeurIPS 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
4042. NeurIPS 2024Self-Calibrating Conformal Prediction
4043. NeurIPS 2024Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
4044. NeurIPS 2024Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
4045. NeurIPS 2024SelfCodeAlign: Self-Alignment for Code Generation
4046. NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
4047. NeurIPS 2024Sequential Harmful Shift Detection Without Labels
4048. NeurIPS 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
4049. NeurIPS 2024SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
4050. NeurIPS 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types

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。