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 551 篇，第 7 / 12 页
- ICML 2026Multilingual Safety Alignment Via Sparse Weight Editing
- ICML 2026Multimodal Fusion via Self-Consistent Task-Gradient Fields
- ICML 2026Multimodal Nested Learning for Decoupled and Coordinated Optimization
- ICML 2026Multimodal Scaling Laws for Task & Data-Optimized Models of Visual Cortex
- ICML 2026Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
- ICML 2026N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout
- ICML 2026Navigating the Pareto Frontier of Alignment: Spectrum-Adaptive Fine-Tuning for LLMs
- ICML 2026Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-Smoothness
- ICML 2026Nested birth-death processes are competitive with neural networks as time-dependent models of protein evolution
- ICML 2026Neural Logistic Bandits
- ICML 2026Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
- ICML 2026Neural-Inspired Modeling of Auditory Selection and Compensation for Audio-Visual Speech Separation
- ICML 2026NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data
- ICML 2026NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
- ICML 2026Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
- ICML 2026Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
- ICML 2026Nonparametric Distribution Regression Re-calibration
- ICML 2026Normalized Rewards for Preference Optimization
- ICML 2026NorMuon: Making Muon more efficient and scalable
- ICML 2026Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
- ICML 2026Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
- ICML 2026OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
- ICML 2026On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis
- ICML 2026On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions
- ICML 2026On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed Communication
- ICML 2026On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach
- ICML 2026One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
- ICML 2026One Probe Won’t Catch Them All: Towards Targeted Deception Detection
- ICML 2026Online Packet Scheduling with Deadlines and Learning
- ICML 2026Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection
- ICML 2026Operationalising the Superficial Alignment Hypothesis via Task Complexity
- ICML 2026Optimal structure learning and conditional independence testing
- ICML 2026Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
- ICML 2026OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
- ICML 2026OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
- ICML 2026OSCS: Online Selection with Provable FAR Control for LLM Safety
- ICML 2026OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
- ICML 2026Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
- ICML 2026Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
- ICML 2026PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
- ICML 2026PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
- ICML 2026PADS-TAL: Padding-Annealed Diffusion Sampling in Text-Aware Latent Space for Robust and Diverse Text-to-Music Generation
- ICML 2026Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting
- ICML 2026Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
- ICML 2026Pareto-Guided Optimal Transport for Multi-Reward Alignment
- ICML 2026Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
- ICML 2026Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal Transport
- ICML 2026Path-conditioned training: a principled way to rescale ReLU neural networks
- ICML 2026Peer-Preservation in Frontier Models
- ICML 2026Per-example Gradients: a New Frontier for Understanding and Improving Optimizers
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。