Alignment and Safety papers, 2023–2026

Key findings

• Alignment and Safety went from 438 papers in 2023 to 1,882 in 2026, roughly 4.3x in three years.
• NeurIPS publishes the most Alignment and Safety work: 1,421 papers from 2023 to 2026, 31% of the four-venue total.
• The fastest-growing overlap is with Social aspects · safety: papers tagged with both rose from 0 in 2023 to 137 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #1 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 4.3x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Alignment and Safety papers

348 papers, page 3 of 7

101. NeurIPS 2024Enhancing Large Vision Language Models with Self-Training on Image Comprehension
102. NeurIPS 2024Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
103. NeurIPS 2024Entity Alignment with Noisy Annotations from Large Language Models
104. NeurIPS 2024Evaluating alignment between humans and neural network representations in image-based learning tasks
105. NeurIPS 2024Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
106. NeurIPS 2024Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
107. NeurIPS 2024Exploiting LLM Quantization
108. NeurIPS 2024Exploring Adversarial Robustness of Deep State Space Models
109. NeurIPS 2024Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
110. NeurIPS 2024Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
111. NeurIPS 2024Fast Best-of-N Decoding via Speculative Rejection
112. NeurIPS 2024Fast yet Safe: Early-Exiting with Risk Control
113. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
114. NeurIPS 2024Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
115. NeurIPS 2024FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
116. NeurIPS 2024FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
117. NeurIPS 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
118. NeurIPS 2024Few-Shot Adversarial Prompt Learning on Vision-Language Models
119. NeurIPS 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning
120. NeurIPS 2024FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
121. NeurIPS 2024FLAME : Factuality-Aware Alignment for Large Language Models
122. NeurIPS 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
123. NeurIPS 2024From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
124. NeurIPS 2024From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
125. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
126. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
127. NeurIPS 2024Generalizable Person Re-identification via Balancing Alignment and Uniformity
128. NeurIPS 2024Geometric-Averaged Preference Optimization for Soft Preference Labels
129. NeurIPS 2024Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
130. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
131. NeurIPS 2024GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
132. NeurIPS 2024Group Robust Preference Optimization in Reward-free RLHF
133. NeurIPS 2024Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
134. NeurIPS 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
135. NeurIPS 2024HelpSteer 2: Open-source dataset for training top-performing reward models
136. NeurIPS 2024HonestLLM: Toward an Honest and Helpful Large Language Model
137. NeurIPS 2024Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
138. NeurIPS 2024HuRef: HUman-REadable Fingerprint for Large Language Models
139. NeurIPS 2024Imitating Language via Scalable Inverse Reinforcement Learning
140. NeurIPS 2024Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
141. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
142. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
143. NeurIPS 2024Improving Alignment and Robustness with Circuit Breakers
144. NeurIPS 2024Improving Context-Aware Preference Modeling for Language Models
145. NeurIPS 2024Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
146. NeurIPS 2024Improving Subgroup Robustness via Data Selection
147. NeurIPS 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
148. NeurIPS 2024InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
149. NeurIPS 2024Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
150. NeurIPS 2024Interpreting Learned Feedback Patterns in Large Language Models

FAQ

How many Alignment and Safety papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

4,558 in total: 438 in 2023, 875 in 2024, 1,363 in 2025, 1,882 in 2026.

How many Alignment and Safety papers are at NeurIPS 2026?

NeurIPS 2026 has 480 Alignment and Safety papers, versus 455 the year before.

How many Alignment and Safety papers are at ICLR 2026?

ICLR 2026 has 623 Alignment and Safety papers, versus 473 the year before.

How many Alignment and Safety papers are at ICML 2026?

ICML 2026 has 551 Alignment and Safety papers, versus 300 the year before.

How many Alignment and Safety papers are at CVPR 2026?

CVPR 2026 has 228 Alignment and Safety papers, versus 135 the year before.

Which conference publishes the most Alignment and Safety papers?

NeurIPS, with 1,421 papers from 2023 to 2026.