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 1,421 篇，第 18 / 29 页

851. NeurIPS 2025Shape it Up! Restoring LLM Safety during Finetuning
852. NeurIPS 2025Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
853. NeurIPS 2025Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
854. NeurIPS 2025Simple and Efficient Heterogeneous Temporal Graph Neural Network
855. NeurIPS 2025Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
856. NeurIPS 2025SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
857. NeurIPS 2025SkyLadder: Better and Faster Pretraining via Context Window Scheduling
858. NeurIPS 2025SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
859. NeurIPS 2025Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
860. NeurIPS 2025Sparta Alignment: Collectively Aligning Multiple Language Models through Combat
861. NeurIPS 2025Spectral Analysis of Representational Similarity with Limited Neurons
862. NeurIPS 2025Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
863. NeurIPS 2025Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
864. NeurIPS 2025Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
865. NeurIPS 2025Stable Matching with Ties: Approximation Ratios and Learning
866. NeurIPS 2025Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
867. NeurIPS 2025Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
868. NeurIPS 2025Stop the Nonconsensual Use of Nude Images in Research
869. NeurIPS 2025Storyboard-guided Alignment for Fine-grained Video Action Recognition
870. NeurIPS 2025Strassen Attention, Split VC Dimension and Compositionality in Transformers
871. NeurIPS 2025Strategyproof Reinforcement Learning from Human Feedback
872. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
873. NeurIPS 2025SuperCLIP: CLIP with Simple Classification Supervision
874. NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
875. NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
876. NeurIPS 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
877. NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
878. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
879. NeurIPS 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
880. NeurIPS 2025The Burden of Interactive Alignment with Inconsistent Preferences
881. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
882. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
883. NeurIPS 2025The Indra Representation Hypothesis
884. NeurIPS 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
885. NeurIPS 2025The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education
886. NeurIPS 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
887. NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
888. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
889. NeurIPS 2025Thresholds for sensitive optimality and Blackwell optimality in stochastic games
890. NeurIPS 2025Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting
891. NeurIPS 2025Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
892. NeurIPS 2025Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
893. NeurIPS 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
894. NeurIPS 2025Token-Level Self-Play with Importance-Aware Guidance for Large Language Models
895. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
896. NeurIPS 2025Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
897. NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
898. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
899. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
900. NeurIPS 2025Training-Free Safe Denoisers for Safe Use of Diffusion Models

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。