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

1,363 papers, page 16 of 28

751. ICML 2025LOGO --- Long cOntext aliGnment via efficient preference Optimization
752. ICML 2025Long-Short Alignment for Effective Long-Context Modeling in LLMs
753. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
754. ICML 2025M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture
755. ICML 2025Measuring Diversity: Axioms and Challenges
756. ICML 2025Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
757. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
758. ICML 2025Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers
759. ICML 2025MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
760. ICML 2025Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries
761. ICML 2025Mixed-curvature decision trees and random forests
762. ICML 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
763. ICML 2025MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization
764. ICML 2025MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
765. ICML 2025MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
766. ICML 2025Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization
767. ICML 2025Nesterov Method for Asynchronous Pipeline Parallel Optimization
768. ICML 2025Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
769. ICML 2025Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment
770. ICML 2025Neural Solver Selection for Combinatorial Optimization
771. ICML 2025No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
772. ICML 2025Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails
773. ICML 2025Novelty Detection in Reinforcement Learning with World Models
774. ICML 2025Observation Interference in Partially Observable Assistance Games
775. ICML 2025Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
776. ICML 2025Offline Model-based Optimization for Real-World Molecular Discovery
777. ICML 2025On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
778. ICML 2025On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
779. ICML 2025On Teacher Hacking in Language Model Distillation
780. ICML 2025On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness
781. ICML 2025On the Robustness of Reward Models for Language Model Alignment
782. ICML 2025On the Similarities of Embeddings in Contrastive Learning
783. ICML 2025On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
784. ICML 2025On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
785. ICML 2025One-Step Generalization Ratio Guided Optimization for Domain Generalization
786. ICML 2025Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics
787. ICML 2025Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
788. ICML 2025OR-Bench: An Over-Refusal Benchmark for Large Language Models
789. ICML 2025PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
790. ICML 2025Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
791. ICML 2025PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
792. ICML 2025PILAF: Optimal Human Preference Sampling for Reward Modeling
793. ICML 2025PIPA: Preference Alignment as Prior-Informed Statistical Estimation
794. ICML 2025PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
795. ICML 2025PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data
796. ICML 2025Policy Filtration for RLHF to Mitigate Noise in Reward Models
797. ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
798. ICML 2025Policy-labeled Preference Learning: Is Preference Enough for RLHF?
799. ICML 2025POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
800. ICML 2025Position: AI Safety Must Embrace an Antifragile Perspective

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.