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 1,339 篇，第 14 / 27 页
- ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
- ICLR 2025Adversarial Search Engine Optimization for Large Language Models
- ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
- ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- ICLR 2025AI Sandbagging: Language Models can Strategically Underperform on Evaluations
- ICLR 2025AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
- ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
- ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
- ICLR 2025Aligning Language Models with Demonstrated Feedback
- ICLR 2025Aligning Visual Contrastive learning models via Preference Optimization
- ICLR 2025ALLaM: Large Language Models for Arabic and English
- ICLR 2025AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
- ICLR 2025Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
- ICLR 2025An Auditing Test to Detect Behavioral Shift in Language Models
- ICLR 2025An Effective Theory of Bias Amplification
- ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
- ICLR 2025An Undetectable Watermark for Generative Image Models
- ICLR 2025Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
- ICLR 2025As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
- ICLR 2025Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
- ICLR 2025Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation
- ICLR 2025Attention with Markov: A Curious Case of Single-layer Transformers
- ICLR 2025AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
- ICLR 2025Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
- ICLR 2025Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
- ICLR 2025Backtracking Improves Generation Safety
- ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
- ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
- ICLR 2025BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
- ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
- ICLR 2025Bayesian WeakS-to-Strong from Text Classification to Generation
- ICLR 2025Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
- ICLR 2025BingoGuard: LLM Content Moderation Tools with Risk Levels
- ICLR 2025Black-Box Detection of Language Model Watermarks
- ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
- ICLR 2025Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
- ICLR 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
- ICLR 2025Bootstrapping Language Models with DPO Implicit Rewards
- ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
- ICLR 2025Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
- ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
- ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
- ICLR 2025Building Math Agents with Multi-Turn Iterative Preference Learning
- ICLR 2025Calibrating Expressions of Certainty
- ICLR 2025Can a Large Language Model be a Gaslighter?
- ICLR 2025Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
- ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
- ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
- ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
- ICLR 2025Can We Ignore Labels in Out of Distribution Detection?
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。