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 1,198 篇，第 20 / 24 页

951. ICML 2024Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification
952. ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
953. ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
954. ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
955. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
956. ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs
957. ICML 2024KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
958. ICML 2024Language Models Represent Beliefs of Self and Others
959. ICML 2024LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
960. ICML 2024Learning and Forgetting Unsafe Examples in Large Language Models
961. ICML 2024Learning Associative Memories with Gradient Descent
962. ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse
963. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
964. ICML 2024Learning Linear Block Error Correction Codes
965. ICML 2024Learning Modality Knowledge Alignment for Cross-Modality Transfer
966. ICML 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
967. ICML 2024Learning to Remove Cuts in Integer Linear Programming
968. ICML 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)
969. ICML 2024Limited Preference Aided Imitation Learning from Imperfect Demonstrations
970. ICML 2024Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
971. ICML 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
972. ICML 2024Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
973. ICML 2024MaxMin-RLHF: Alignment with Diverse Human Preferences
974. ICML 2024Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization
975. ICML 2024MGit: A Model Versioning and Management System
976. ICML 2024Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
977. ICML 2024MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation
978. ICML 2024Model Alignment as Prospect Theoretic Optimization
979. ICML 2024Model Assessment and Selection under Temporal Distribution Shift
980. ICML 2024Momentum Particle Maximum Likelihood
981. ICML 2024Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks
982. ICML 2024Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy
983. ICML 2024MusicRL: Aligning Music Generation to Human Preferences
984. ICML 2024Naive Bayes Classifiers over Missing Data: Decision and Poisoning
985. ICML 2024Nash Learning from Human Feedback
986. ICML 2024Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
987. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
988. ICML 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF
989. ICML 2024On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
990. ICML 2024On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
991. ICML 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Training
992. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
993. ICML 2024Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
994. ICML 2024Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
995. ICML 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
996. ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
997. ICML 2024OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
998. ICML 2024Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors
999. ICML 2024Pairwise Alignment Improves Graph Domain Adaptation
1000. ICML 2024PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition

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。