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 12 / 28 页

551. ICLR 2025Test-time Alignment of Diffusion Models without Reward Over-optimization
552. ICLR 2025The Crucial Role of Samplers in Online Direct Preference Optimization
553. ICLR 2025The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
554. ICLR 2025The Geometry of Categorical and Hierarchical Concepts in Large Language Models
555. ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
556. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
557. ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
558. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
559. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
560. ICLR 2025TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
561. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
562. ICLR 2025To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
563. ICLR 2025TODO: Enhancing LLM Alignment with Ternary Preferences
564. ICLR 2025Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
565. ICLR 2025Towards a learning theory of representation alignment
566. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
567. ICLR 2025Towards counterfactual fairness through auxiliary variables
568. ICLR 2025Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
569. ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
570. ICLR 2025Towards hyperparameter-free optimization with differential privacy
571. ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
572. ICLR 2025Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
573. ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
574. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
575. ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
576. ICLR 2025Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
577. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
578. ICLR 2025Training-Free Diffusion Model Alignment with Sampling Demons
579. ICLR 2025Training-free LLM-generated Text Detection by Mining Token Probability Sequences
580. ICLR 2025Transformers Learn Low Sensitivity Functions: Investigations and Implications
581. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
582. ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
583. ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
584. ICLR 2025Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
585. ICLR 2025Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
586. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
587. ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
588. ICLR 2025UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
589. ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
590. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
591. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
592. ICLR 2025Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
593. ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
594. ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
595. ICLR 2025Variational Best-of-N Alignment
596. ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
597. ICLR 2025VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
598. ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
599. ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
600. ICLR 2025Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations

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。