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 1,339 篇，第 6 / 27 页
- ICLR 2026Gradient Intrinsic Dimensionality Alignment：Narrowing The Gap Between Low-Rank Adaptation and Full Fine-Tuning
- ICLR 2026GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
- ICLR 2026GradShield: Alignment Preserving Finetuning
- ICLR 2026GraphShield: Graph-Theoretic Modeling of Network-Level Dynamics for Robust Jailbreak Detection
- ICLR 2026Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
- ICLR 2026GuardAlign: Robust Safety Alignment in Multimodal Large Language Models
- ICLR 2026GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
- ICLR 2026HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
- ICLR 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
- ICLR 2026HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction
- ICLR 2026Hot PATE: Private Aggregation of Distributions for Diverse Tasks
- ICLR 2026How Catastrophic is Your LLM? Certifying Risk in Conversation
- ICLR 2026How Dark Patterns Manipulate Web Agents
- ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
- ICLR 2026Hubble: a Model Suite to Advance the Study of LLM Memorization
- ICLR 2026Human-AI Curation Synergy: Scaling Preference Data Curation via Human-Guided AI Feedback
- ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
- ICLR 2026Humanline: Online Alignment as Perceptual Loss
- ICLR 2026IA2: Alignment with ICL Activations improves Supervised Fine-Tuning
- ICLR 2026ICPO: Provable and Practical In-Context Policy Optimization for Test-Time Scaling
- ICLR 2026Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
- ICLR 2026Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization
- ICLR 2026ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
- ICLR 2026Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment
- ICLR 2026In-Context Watermarks for Large Language Models
- ICLR 2026Incentive-Aligned LLM Summaries
- ICLR 2026Inconsistency Biases in Dynamic Data Pruning
- ICLR 2026Inference-Time Personalized Safety Control via Paired Difference-in-Means Intervention
- ICLR 2026INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
- ICLR 2026Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-time
- ICLR 2026INTIMA: A Benchmark for Human-AI Companionship Behavior
- ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
- ICLR 2026Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
- ICLR 2026Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
- ICLR 2026Is On-Policy Data always the Best Choice for Direct Preference Optimization-Based LM Alignment?
- ICLR 2026Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
- ICLR 2026It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
- ICLR 2026Jailbreak Transferability Emerges from Shared Representations
- ICLR 2026Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
- ICLR 2026Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
- ICLR 2026JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe
- ICLR 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
- ICLR 2026JULI: Jailbreak Large Language Models by Self-Introspection
- ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
- ICLR 2026K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
- ICLR 2026Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization
- ICLR 2026Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
- ICLR 2026Label Smoothing Improves Machine Unlearning
- ICLR 2026Large Language Model Compression with Global Rank and Sparsity Optimization
- ICLR 2026Latent Speech-Text Transformer
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。