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 83 / 92 页
- NeurIPS 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
- NeurIPS 2024Verifiably Robust Conformal Prediction
- NeurIPS 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Models
- NeurIPS 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
- NeurIPS 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
- NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
- NeurIPS 2024Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
- NeurIPS 2024WeiPer: OOD Detection using Weight Perturbations of Class Projections
- NeurIPS 2024What If the Input is Expanded in OOD Detection?
- NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
- NeurIPS 2024When does perceptual alignment benefit vision representations?
- NeurIPS 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
- NeurIPS 2024When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
- NeurIPS 2024Who's asking? User personas and the mechanics of latent misalignment
- NeurIPS 2024WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
- NeurIPS 2024Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
- NeurIPS 2024Your contrastive learning problem is secretly a distribution alignment problem
- NeurIPS 2024ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
- CVPR 2023A Meta-Learning Approach to Predicting Performance and Data Requirements
- CVPR 2023A Unified HDR Imaging Method With Pixel and Patch Level
- CVPR 2023A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance
- CVPR 2023Adjustment and Alignment for Unbiased Open Set Domain Adaptation
- CVPR 2023Advancing Visual Grounding With Scene Knowledge: Benchmark and Method
- CVPR 2023Align and Attend: Multimodal Summarization With Dual Contrastive Losses
- CVPR 2023An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions
- CVPR 2023Analyzing and Diagnosing Pose Estimation With Attributions
- CVPR 2023Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning
- CVPR 2023Automatic High Resolution Wire Segmentation and Removal
- CVPR 2023BASiS: Batch Aligned Spectral Embedding Space
- CVPR 2023Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning
- CVPR 2023Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration
- CVPR 2023Blemish-Aware and Progressive Face Retouching With Limited Paired Data
- CVPR 2023Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping
- CVPR 2023Burstormer: Burst Image Restoration and Enhancement Transformer
- CVPR 2023CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss
- CVPR 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
- CVPR 2023CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning
- CVPR 2023CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose
- CVPR 2023Clover: Towards a Unified Video-Language Alignment and Fusion Model
- CVPR 2023Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting
- CVPR 2023Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation
- CVPR 2023Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training
- CVPR 2023CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment
- CVPR 2023Decoupling Human and Camera Motion From Videos in the Wild
- CVPR 2023Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric
- CVPR 2023Deep Incomplete Multi-View Clustering With Cross-View Partial Sample and Prototype Alignment
- CVPR 2023Defining and Quantifying the Emergence of Sparse Concepts in DNNs
- CVPR 2023Diffusion-Based Generation, Optimization, and Planning in 3D Scenes
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。