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 600 篇，第 6 / 12 页
- CVPR 2025Can Text-to-Video Generation help Video-Language Alignment?
- CVPR 2025CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
- CVPR 2025Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment
- CVPR 2025Chebyshev Attention Depth Permutation Texture Network with Latent Texture Attribute Loss
- CVPR 2025ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
- CVPR 2025Continual SFT Matches Multimodal RLHF with Negative Supervision
- CVPR 2025Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
- CVPR 2025CrossOver: 3D Scene Cross-Modal Alignment
- CVPR 2025Curriculum Direct Preference Optimization for Diffusion and Consistency Models
- CVPR 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
- CVPR 2025Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
- CVPR 2025Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
- CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
- CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
- CVPR 2025Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality
- CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
- CVPR 2025Doppelgangers and Adversarial Vulnerability
- CVPR 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
- CVPR 2025EBS-EKF: Accurate and High Frequency Event-based Star Tracking
- CVPR 2025EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
- CVPR 2025Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework
- CVPR 2025Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation
- CVPR 2025Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces
- CVPR 2025EventPSR: Surface Normal and Reflectance Estimation from Photometric Stereo Using an Event Camera
- CVPR 2025Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
- CVPR 2025Flexible Group Count Enables Hassle-Free Structured Pruning
- CVPR 2025Font-Agent: Enhancing Font Understanding with Large Language Models
- CVPR 2025Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution
- CVPR 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
- CVPR 2025HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
- CVPR 2025Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching
- CVPR 2025HOT: Hadamard-based Optimized Training
- CVPR 2025Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
- CVPR 2025HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
- CVPR 2025Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
- CVPR 2025Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
- CVPR 2025Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity
- CVPR 2025Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning
- CVPR 2025Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models
- CVPR 2025InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
- CVPR 2025iSegMan: Interactive Segment-and-Manipulate 3D Gaussians
- CVPR 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learning
- CVPR 2025JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems
- CVPR 2025Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning
- CVPR 2025LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation
- CVPR 2025Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model
- CVPR 2025Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References
- CVPR 2025Let's Verify and Reinforce Image Generation Step by Step
- CVPR 2025Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
- CVPR 2025MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing
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。