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

1,339 papers, page 13 of 27

601. ICLR 2026WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
602. ICLR 2026Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
603. ICLR 2026Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
604. ICLR 2026WaterDrum: Watermark-based Data-centric Unlearning Metric
605. ICLR 2026Watermark-based Attribution of AI-Generated Content
606. ICLR 2026Weak-to-Strong Generalization with Failure Trajectories
607. ICLR 2026What Do Large Language Models Know About Opinions?
608. ICLR 2026What happens when generative AI models train recursively on each others' outputs?
609. ICLR 2026What matters for Representation Alignment: Global Information or Spatial Structure?
610. ICLR 2026What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
611. ICLR 2026What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation
612. ICLR 2026When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
613. ICLR 2026When Language Models Lose Their Mind: The Consequences of Brain Misalignment
614. ICLR 2026When Machine Learning Gets Personal: Evaluating Prediction and Explanation
615. ICLR 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining
616. ICLR 2026When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
617. ICLR 2026When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
618. ICLR 2026Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
619. ICLR 2026Why DPO is a Misspecified Estimator and How to Fix It
620. ICLR 2026Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
621. ICLR 2026Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
622. ICLR 2026Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
623. ICLR 2026Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
624. ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
625. ICLR 2025$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
626. ICLR 20253D-Properties: Identifying Challenges in DPO and Charting a Path Forward
627. ICLR 2025A Benchmark for Semantic Sensitive Information in LLMs Outputs
628. ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
629. ICLR 2025A Closer Look at Machine Unlearning for Large Language Models
630. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
631. ICLR 2025A Generic Framework for Conformal Fairness
632. ICLR 2025A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
633. ICLR 2025A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
634. ICLR 2025A Simple yet Effective $\Delta\Delta G$ Predictor is An Unsupervised Antibody Optimizer and Explainer
635. ICLR 2025A Theoretical Framework for Partially-Observed Reward States in RLHF
636. ICLR 2025A Transfer Attack to Image Watermarks
637. ICLR 2025A transfer learning framework for weak to strong generalization
638. ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
639. ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
640. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
641. ICLR 2025Adam-mini: Use Fewer Learning Rates To Gain More
642. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
643. ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
644. ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
645. ICLR 2025Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
646. ICLR 2025Advancing LLM Reasoning Generalists with Preference Trees
647. ICLR 2025Advantage-Guided Distillation for Preference Alignment in Small Language Models
648. ICLR 2025Adversarial Attacks on Data Attribution
649. ICLR 2025Adversarial Latent Feature Augmentation for Fairness
650. ICLR 2025Adversarial Machine Unlearning

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.