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

1,198 papers, page 13 of 24

601. ICML 2025Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
602. ICML 2025Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
603. ICML 2025Compressing tree ensembles through Level-wise Optimization and Pruning
604. ICML 2025Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
605. ICML 2025Conformal Tail Risk Control for Large Language Model Alignment
606. ICML 2025ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
607. ICML 2025Constrain Alignment with Sparse Autoencoders
608. ICML 2025Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach
609. ICML 2025Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
610. ICML 2025Cross-City Latent Space Alignment for Consistency Region Embedding
611. ICML 2025CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
612. ICML 2025DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
613. ICML 2025DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning
614. ICML 2025Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
615. ICML 2025Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
616. ICML 2025Design Considerations in Offline Preference-based RL
617. ICML 2025Differentiable Quadratic Optimization For the Maximum Independent Set Problem
618. ICML 2025Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
619. ICML 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
620. ICML 2025Discrete and Continuous Difference of Submodular Minimization
621. ICML 2025Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
622. ICML 2025Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold
623. ICML 2025Diverging Preferences: When do Annotators Disagree and do Models Know?
624. ICML 2025Don't Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters
625. ICML 2025DPO Meets PPO: Reinforced Token Optimization for RLHF
626. ICML 2025DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
627. ICML 2025Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
628. ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
629. ICML 2025Eliciting Language Model Behaviors with Investigator Agents
630. ICML 2025ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
631. ICML 2025ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
632. ICML 2025Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
633. ICML 2025Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
634. ICML 2025Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization
635. ICML 2025Enhancing Parallelism in Decentralized Stochastic Convex Optimization
636. ICML 2025Enhancing Spectral GNNs: From Topology and Perturbation Perspectives
637. ICML 2025EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
638. ICML 2025EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
639. ICML 2025Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
640. ICML 2025Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects
641. ICML 2025Explicit Preference Optimization: No Need for an Implicit Reward Model
642. ICML 2025Faster Global Minimum Cut with Predictions
643. ICML 2025Features are fate: a theory of transfer learning in high-dimensional regression
644. ICML 2025FlipAttack: Jailbreak LLMs via Flipping
645. ICML 2025Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics
646. ICML 2025Functional Alignment Can Mislead: Examining Model Stitching
647. ICML 2025Fusing Reward and Dueling Feedback in Stochastic Bandits
648. ICML 2025Gandalf the Red: Adaptive Security for LLMs
649. ICML 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
650. ICML 2025Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization

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.