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 1,421 篇，第 7 / 29 页
- NeurIPS 2026PortPy: A Benchmark for AI and Optimization in Cancer Radiotherapy Planning
- NeurIPS 2026PoSafeNet: Structured Safety Learning via Compositional Projection
- NeurIPS 2026Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
- NeurIPS 2026Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
- NeurIPS 2026Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
- NeurIPS 2026Post-hoc Selective Classification for Reliable Synthetic Image Detection
- NeurIPS 2026Prediction-Intervention Games and Invariant Sets
- NeurIPS 2026Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
- NeurIPS 2026Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving
- NeurIPS 2026Pretraining Curricula Enable Selective Fine-tuning
- NeurIPS 2026Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
- NeurIPS 2026PRISM: Phenotype-Resolved Inference in Single-Cell Mixed Models via Latent Disease States and Contextualized Differential Expression
- NeurIPS 2026PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
- NeurIPS 2026PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning
- NeurIPS 2026PRISMIC: Reconstructing User Preference via Intent Decomposition and Consolidation
- NeurIPS 2026PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
- NeurIPS 2026ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification
- NeurIPS 2026PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
- NeurIPS 2026ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
- NeurIPS 2026ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
- NeurIPS 2026Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
- NeurIPS 2026Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
- NeurIPS 2026RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
- NeurIPS 2026RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
- NeurIPS 2026RealityTest: How People Probe AI Identity and Whether Models Disclose It
- NeurIPS 2026Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
- NeurIPS 2026Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
- NeurIPS 2026ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
- NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
- NeurIPS 2026Region-Normalized DPO for Medical Image Segmentation
- NeurIPS 2026Reliable Clustering and Quantization via Distortion-Constrained Optimal Transport
- NeurIPS 2026Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
- NeurIPS 2026RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation
- NeurIPS 2026Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
- NeurIPS 2026Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
- NeurIPS 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
- NeurIPS 2026Resolution-Aware Structural Density Peak Clustering
- NeurIPS 2026Rethinking CT Synthesis through Semantics-Structure Alignment
- NeurIPS 2026Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
- NeurIPS 2026Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models
- NeurIPS 2026Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
- NeurIPS 2026Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
- NeurIPS 2026Rethinking Sequential Locate-Then-Edit: Optimality and Stability
- NeurIPS 2026Revisiting Decentralized Online Convex Optimization with Compressed Communication
- NeurIPS 2026Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
- NeurIPS 2026Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
- NeurIPS 2026RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
- NeurIPS 2026Risk-Sensitive Deep Optimal Stopping
- NeurIPS 2026RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
- NeurIPS 2026Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration
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。