对齐与安全论文趋势 2023–2026
RLHF、偏好优化、红队与安全对齐
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 4,558 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 138 | 87 | 101 | 112 | 438 |
| 2024 | 348 | 156 | 246 | 125 | 875 |
| 2025 | 455 | 473 | 300 | 135 | 1,363 |
| 2026 | 480 | 623 | 551 | 228 | 1,882 |
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 12 / 92 页
- ICLR 2026Log Probability Tracking of LLM APIs
- ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
- ICLR 2026Low-Pass Filtering Improves Behavioral Alignment of Vision Models
- ICLR 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
- ICLR 2026ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
- ICLR 2026Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
- ICLR 2026MATRIX: Mask Track Alignment for Interaction-aware Video Generation
- ICLR 2026MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
- ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
- ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
- ICLR 2026Membership Privacy Risks of Sharpness Aware Minimization
- ICLR 2026Memorization Through the Lens of Sample Gradients
- ICLR 2026MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
- ICLR 2026Meta-Router: Bridging Gold-standard and Preference-based Evaluations in LLM Routing
- ICLR 2026MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
- ICLR 2026Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
- ICLR 2026Mitigating Mismatch within Reference-based Preference Optimization
- ICLR 2026Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
- ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
- ICLR 2026Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
- ICLR 2026MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference
- ICLR 2026MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
- ICLR 2026Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
- ICLR 2026Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
- ICLR 2026Modality-free Graph In-context Alignment
- ICLR 2026Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
- ICLR 2026MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
- ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors
- ICLR 2026More Than What Was Chosen: LLM-based Explainable Recommendation Beyond Noisy User Preferences
- ICLR 2026MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
- ICLR 2026mR3: Multilingual Rubric-Agnostic Reward Reasoning Models
- ICLR 2026Multi-Feature Quantized Self-Attention for Fair Large Language Models
- ICLR 2026Multi-objective Large Language Model Alignment with Hierarchical Experts
- ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
- ICLR 2026Multiplayer Nash Preference Optimization
- ICLR 2026Narrow Finetuning Leaves Clearly Readable Traces in the Activation Differences
- ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
- ICLR 2026NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection
- ICLR 2026Neologism Learning for Controllability and Self-Verbalization
- ICLR 2026NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
- ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
- ICLR 2026Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
- ICLR 2026Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
- ICLR 2026NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context
- ICLR 2026Obfuscated Activations Bypass LLM Latent-Space Defenses
- ICLR 2026Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
- ICLR 2026OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
- ICLR 2026OFMU: OPTIMIZATION-DRIVEN FRAMEWORK FOR MACHINE UNLEARNING
- ICLR 2026Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
- ICLR 2026OmniPortrait: Fine-Grained Personalized Portrait Synthesis via Pivotal Optimization
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查对齐与安全在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "alignment-and-safety"}
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。