对齐与安全论文趋势 2023–2026

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。

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 3 / 12 页

101. ICML 2026Corrigibility Transformation: Constructing Goals That Accept Updates
102. ICML 2026Cost-aware Stopping for Bayesian Optimization
103. ICML 2026Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning
104. ICML 2026Coverage Improvement and Fast Convergence of On-policy Preference Learning
105. ICML 2026Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
106. ICML 2026Cycle-of-Science: Reliable Reasoning through Counterfactual Verification for Agent Decision Making
107. ICML 2026D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
108. ICML 2026d$^2$p: Structured Soft Attention Is All You Need
109. ICML 2026DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
110. ICML 2026DART: Distribution-Aware Adaptive Relational Transfer for Adversarial Attacks against Closed-Source MLLMs
111. ICML 2026Data Reconstruction: Identifiability and Optimization with Sample Splitting
112. ICML 2026Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
113. ICML 2026Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
114. ICML 2026Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
115. ICML 2026Decentralized Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower Bounds
116. ICML 2026DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and Exploitation
117. ICML 2026Decoupling The "What" and "Where" With Polar Coordinate Positional Embedding
118. ICML 2026Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
119. ICML 2026Deep Flow Networks
120. ICML 2026Delving into Muon and Beyond: Deep Analysis and Extensions
121. ICML 2026Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
122. ICML 2026Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
123. ICML 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
124. ICML 2026Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
125. ICML 2026DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
126. ICML 2026Differential syntactic and semantic encoding in LLMs
127. ICML 2026Differentially Private Preference Data Synthesis for Large Language Model Alignment
128. ICML 2026Discovering Implicit Large Language Model Alignment Objectives
129. ICML 2026Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
130. ICML 2026Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
131. ICML 2026DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
132. ICML 2026Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
133. ICML 2026Dissecting Quantization Error: A Concentration-Alignment Perspective
134. ICML 2026Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMs
135. ICML 2026Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
136. ICML 2026Distributed Direct Preference Optimization
137. ICML 2026Distributed Stochastic $K$-Level Optimization Over Networks
138. ICML 2026Distribution Alignment for One-Shot Federated Learning via Optimal Transport
139. ICML 2026Distributional Alignment Games for Answer-Level Fine-Tuning
140. ICML 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
141. ICML 2026Distributionally Robust Reinforcement Learning from Human Feedback
142. ICML 2026Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
143. ICML 2026Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
144. ICML 2026DMCO: Budget-Aware Co-Optimization of Data Cleaning and AutoML
145. ICML 2026Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox
146. ICML 2026Domain Transfer Becomes Identifiable via a Single Alignment
147. ICML 2026Don't Walk the Line: Boundary Guidance for Filtered Generation
148. ICML 2026DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable)
149. ICML 2026Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
150. ICML 2026dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

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。