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

4,558 papers, page 56 of 92

2751. ICML 2025Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
2752. ICML 2025TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization
2753. ICML 2025Test-time Correlation Alignment
2754. ICML 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
2755. ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
2756. ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
2757. ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
2758. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
2759. ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
2760. ICML 2025The Limits of Predicting Agents from Behaviour
2761. ICML 2025The Lock-in Hypothesis: Stagnation by Algorithm
2762. ICML 2025The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
2763. ICML 2025The Missing Alignment Link of In-context Learning on Sequences
2764. ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
2765. ICML 2025The Relationship Between No-Regret Learning and Online Conformal Prediction
2766. ICML 2025Theoretical guarantees on the best-of-n alignment policy
2767. ICML 2025Thinking LLMs: General Instruction Following with Thought Generation
2768. ICML 2025TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
2769. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
2770. ICML 2025Topological Signatures of Adversaries in Multimodal Alignments
2771. ICML 2025Towards an Explainable Comparison and Alignment of Feature Embeddings
2772. ICML 2025Towards Cost-Effective Reward Guided Text Generation
2773. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
2774. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
2775. ICML 2025Training Deep Learning Models with Norm-Constrained LMOs
2776. ICML 2025Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
2777. ICML 2025Transformative or Conservative? Conservation laws for ResNets and Transformers
2778. ICML 2025TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
2779. ICML 2025TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
2780. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
2781. ICML 2025Unconstrained Robust Online Convex Optimization
2782. ICML 2025Understanding High-Dimensional Bayesian Optimization
2783. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
2784. ICML 2025Understanding the Emergence of Multimodal Representation Alignment
2785. ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
2786. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
2787. ICML 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
2788. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
2789. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
2790. ICML 2025When, Where and Why to Average Weights?
2791. NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
2792. NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
2793. NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
2794. NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
2795. NeurIPS 2025A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
2796. NeurIPS 2025A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity
2797. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
2798. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
2799. NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
2800. NeurIPS 2025AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

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.