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 76 of 92

3751. ICML 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
3752. ICML 2024Topological Neural Networks go Persistent, Equivariant, and Continuous
3753. ICML 2024Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components
3754. ICML 2024Towards Efficient Exact Optimization of Language Model Alignment
3755. ICML 2024Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
3756. ICML 2024Towards Modular LLMs by Building and Reusing a Library of LoRAs
3757. ICML 2024Towards Scalable and Versatile Weight Space Learning
3758. ICML 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
3759. ICML 2024Transformers, parallel computation, and logarithmic depth
3760. ICML 2024Transforming and Combining Rewards for Aligning Large Language Models
3761. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
3762. ICML 2024Understanding MLP-Mixer as a wide and sparse MLP
3763. ICML 2024Understanding the Learning Dynamics of Alignment with Human Feedback
3764. ICML 2024Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
3765. ICML 2024Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
3766. ICML 2024Verifying message-passing neural networks via topology-based bounds tightening
3767. ICML 2024WARM: On the Benefits of Weight Averaged Reward Models
3768. ICML 2024Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
3769. ICML 2024Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
3770. ICML 2024What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
3771. ICML 2024When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
3772. ICML 2024When Will Gradient Regularization Be Harmful?
3773. NeurIPS 2024$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
3774. NeurIPS 20243D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
3775. NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
3776. NeurIPS 2024A Novel Benchmark for Decision-Making in Uncertain and Competitive Games
3777. NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
3778. NeurIPS 2024A teacher-teacher framework for clinical language representation learning
3779. NeurIPS 2024A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
3780. NeurIPS 2024A Theoretical Understanding of Self-Correction through In-context Alignment
3781. NeurIPS 2024Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
3782. NeurIPS 2024Achieving Domain-Independent Certified Robustness via Knowledge Continuity
3783. NeurIPS 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
3784. NeurIPS 2024Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
3785. NeurIPS 2024Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
3786. NeurIPS 2024Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
3787. NeurIPS 2024Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
3788. NeurIPS 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
3789. NeurIPS 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detection
3790. NeurIPS 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
3791. NeurIPS 2024Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
3792. NeurIPS 2024Aligner: Efficient Alignment by Learning to Correct
3793. NeurIPS 2024Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
3794. NeurIPS 2024Aligning Large Language Models with Representation Editing: A Control Perspective
3795. NeurIPS 2024Aligning Model Properties via Conformal Risk Control
3796. NeurIPS 2024Aligning to Thousands of Preferences via System Message Generalization
3797. NeurIPS 2024Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
3798. NeurIPS 2024Alignment for Honesty
3799. NeurIPS 2024Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
3800. NeurIPS 2024ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users

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.