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 6 / 92 页
- ICLR 2026Aligning Deep Implicit Preferences by Learning to Reason Defensively
- ICLR 2026Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
- ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
- ICLR 2026Alignment-Weighted DPO: A principled reasoning approach to improve alignment
- ICLR 2026AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
- ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
- ICLR 2026All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
- ICLR 2026AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
- ICLR 2026AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
- ICLR 2026Annotation-Efficient Honesty Alignment via Confidence Elicitation and Calibration
- ICLR 2026Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
- ICLR 2026Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
- ICLR 2026Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
- ICLR 2026Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
- ICLR 2026Are Deep Speech Denoising Models Robust to Adversarial Noise?
- ICLR 2026ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
- ICLR 2026ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
- ICLR 2026ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
- ICLR 2026ASIDE: Architectural Separation of Instructions and Data in Language Models
- ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
- ICLR 2026Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
- ICLR 2026Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
- ICLR 2026Attention Smoothing Is All You Need For Unlearning
- ICLR 2026AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion Models
- ICLR 2026AttTok: Marrying Attribute Tokens with Generative Pre-trained Vision-Language Models towards Medical Image Understanding
- ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
- ICLR 2026Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
- ICLR 2026Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies
- ICLR 2026AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
- ICLR 2026Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
- ICLR 2026Balancing the Experts: Unlocking LoRA-MoE for GRPO via Mechanism-Aware Rewards
- ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
- ICLR 2026BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
- ICLR 2026BaseReward: A Strong Baseline for Multimodal Reward Model
- ICLR 2026Batch and Sequential Unlearning for Neural Networks
- ICLR 2026Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
- ICLR 2026Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
- ICLR 2026Benchmarking Open-ended Segmentation
- ICLR 2026Benchmarking Overton Pluralism in LLMs
- ICLR 2026Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
- ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
- ICLR 2026Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
- ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
- ICLR 2026Beyond Pairwise: Empowering LLM Alignment With (Ranked) Choice Modeling
- ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
- ICLR 2026Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
- ICLR 2026Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
- ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
- ICLR 2026Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
- ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
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。