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 55 / 92 页

2701. ICML 2025Progressively Label Enhancement for Large Language Model Alignment
2702. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
2703. ICML 2025ProSec: Fortifying Code LLMs with Proactive Security Alignment
2704. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
2705. ICML 2025Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
2706. ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
2707. ICML 2025R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
2708. ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
2709. ICML 2025RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
2710. ICML 2025Reducing Tool Hallucination via Reliability Alignment
2711. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
2712. ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
2713. ICML 2025Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
2714. ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
2715. ICML 2025Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
2716. ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
2717. ICML 2025Risk and cross validation in ridge regression with correlated samples
2718. ICML 2025RLTHF: Targeted Human Feedback for LLM Alignment
2719. ICML 2025ROPO: Robust Preference Optimization for Large Language Models
2720. ICML 2025RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
2721. ICML 2025RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
2722. ICML 2025SAE-V: Interpreting Multimodal Models for Enhanced Alignment
2723. ICML 2025Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
2724. ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
2725. ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
2726. ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
2727. ICML 2025Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
2728. ICML 2025Safety Reasoning with Guidelines
2729. ICML 2025Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
2730. ICML 2025Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
2731. ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
2732. ICML 2025Self-Consistency Preference Optimization
2733. ICML 2025Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
2734. ICML 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
2735. ICML 2025SEMU: Singular Value Decomposition for Efficient Machine Unlearning
2736. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
2737. ICML 2025SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
2738. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
2739. ICML 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
2740. ICML 2025Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
2741. ICML 2025Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
2742. ICML 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
2743. ICML 2025SPRI: Aligning Large Language Models with Context-Situated Principles
2744. ICML 2025Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
2745. ICML 2025STAIR: Improving Safety Alignment with Introspective Reasoning
2746. ICML 2025Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
2747. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
2748. ICML 2025Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
2749. ICML 2025SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
2750. ICML 2025Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales

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。