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 19 / 28 页

901. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
902. ICML 2025Understanding the Emergence of Multimodal Representation Alignment
903. ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
904. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
905. ICML 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
906. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
907. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
908. ICML 2025When, Where and Why to Average Weights?
909. NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
910. NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
911. NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
912. NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
913. NeurIPS 2025A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
914. NeurIPS 2025A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity
915. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
916. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
917. NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
918. NeurIPS 2025AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
919. NeurIPS 2025Accident Anticipation via Temporal Occurrence Prediction
920. NeurIPS 2025Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
921. NeurIPS 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
922. NeurIPS 2025Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
923. NeurIPS 2025Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
924. NeurIPS 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
925. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
926. NeurIPS 2025AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering
927. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
928. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
929. NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
930. NeurIPS 2025AI-Generated Video Detection via Perceptual Straightening
931. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
932. NeurIPS 2025Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
933. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
934. NeurIPS 2025Aligning Text to Image in Diffusion Models is Easier Than You Think
935. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
936. NeurIPS 2025Alignment of Large Language Models with Constrained Learning
937. NeurIPS 2025AliO: Output Alignment Matters in Long-Term Time Series Forecasting
938. NeurIPS 2025ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
939. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
940. NeurIPS 2025An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
941. NeurIPS 2025Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
942. NeurIPS 2025Angular Steering: Behavior Control via Rotation in Activation Space
943. NeurIPS 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
944. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
945. NeurIPS 2025Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
946. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
947. NeurIPS 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
948. NeurIPS 2025Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
949. NeurIPS 2025AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
950. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

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。