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 4 / 92 页
- CVPR 2026Rethinking Cross-Modal Anchor Alignment for Mitigating Error Accumulation
- CVPR 2026Rethinking SNN Online Training and Deployment Gradient-Coherent Learning via Hybrid-Driven
- CVPR 2026Revisiting Learning with Noisy Labels Active Forgetting and Noise Suppression
- CVPR 2026Revisiting Unknowns Towards Effective and Efficient Open-Set Active Learning
- CVPR 2026Reward Sharpness-Aware Fine-Tuning for Diffusion Models
- CVPR 2026RGB-Event based Pedestrian Attribute Recognition A Benchmark Dataset and An
- CVPR 2026RINO Rotation-Invariant Non-Rigid Correspondences
- CVPR 2026Robo-SGG Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene
- CVPR 2026RoboTAG End-to-end Robot Pose Estimation via Topological Alignment Graph
- CVPR 2026SafeGRPO Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
- CVPR 2026SAIL Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense
- CVPR 2026SAR2Net Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain Alignment
- CVPR 2026SAVA-X Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and
- CVPR 2026SEA-Flow3D Simplified Efficient and Accurate Scene Flow via Spatial Vector
- CVPR 2026Seeing Both Sides Towards Bidirectional Semantic Alignment for Open-Vocabulary Camouflaged
- CVPR 2026Seeing Depth Through Frequency and Motion A Progressive Training Paradigm
- CVPR 2026Seeing without Pixels Perception from Camera Trajectories
- CVPR 2026Select Hypothesize and Verify Towards Verified Neuron Concept Interpretation
- CVPR 2026Selection-as-Nonlinearity Bridging Attention and Activation via a Joint Game-Decision Lens
- CVPR 2026SemiGDA Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation
- CVPR 2026SHOW3D Capturing Scenes of 3D Hands and Objects in the
- CVPR 2026SketchAssist A Practical Assistant for Semantic Edits and Precise Local
- CVPR 2026SMAP Semantic Route Planning with Map-Grounded Multimodal Alignment
- CVPR 2026SMRABooth Subject and Motion Representation Alignment for Customized Video Generation
- CVPR 2026SPAN Spatial-Projection Alignment for Monocular 3D Object Detection
- CVPR 2026SPARROW Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded
- CVPR 2026Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation
- CVPR 2026SplitFlux Learning to Decouple Content and Style from a Single
- CVPR 2026SRA 2 Variational Autoencoder Self-Representation Alignment for Efficient Diffusion
- CVPR 2026Stable Spike Dual Consistency Optimization via Bitwise AND Operations for
- CVPR 2026Stake the Points Structure-Faithful Instance Unlearning
- CVPR 2026STCast Adaptive Boundary Alignment for Global and Regional Weather Forecasting
- CVPR 2026Stealing Split Learning Bottom Models by Recovering Embedding Geometry
- CVPR 2026StreamReady Learning What to Answer and When in Long Streaming
- CVPR 2026Style-GRPO Semantic-Aware Preference Optimization for Image Style Transfer Guided by
- CVPR 2026StyleGallery Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image
- CVPR 2026Tackling Alignment Ambiguity in Person Retrieval through Conversational Attribute Mining
- CVPR 2026TAMER A Tri-Modal Contrastive Alignment and Multi-Scale Embedding Refinement Framework
- CVPR 2026Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal
- CVPR 2026TEAR Temporal-aware Automated Red-teaming for Text-to-Video Models
- CVPR 2026Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning
- CVPR 2026TF-CADE Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection
- CVPR 2026THE MORE THE MERRIER CONTRASTIVE FUSION FOR HIGHER-ORDER MULTIMODAL ALIGNMENT
- CVPR 2026The Power of Decaying Steps Enhancing Attack Stability and Transferability
- CVPR 2026Thermal is Always Wild Characterizing and Addressing Challenges in Thermal-Only
- CVPR 2026Time-Specialized Event-Image Alignment for Blur-to-Video Decomposition
- CVPR 2026Token Reduction via Local and Global Contexts Optimization for Efficient
- CVPR 2026Tokenization Allows Multimodal Large Language Models to Understand Generate and
- CVPR 2026Towards Cross-Modal Preservation Consistency and Alignment for Privacy-Preserving Visible-Infrared Person
- CVPR 2026Towards Dynamic Modality Alignment in Multimodal Continual Learning
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。