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

1,882 papers, page 10 of 38

451. ICLR 2026Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
452. ICLR 2026FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
453. ICLR 2026FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment
454. ICLR 2026FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking
455. ICLR 2026Fluent Alignment with Disfluent Judges: Post-training for lower-resource languages
456. ICLR 2026Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
457. ICLR 2026Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility
458. ICLR 2026From Evaluation to Defense: Advancing Safety in Video Large Language Models
459. ICLR 2026From Natural Alignment to Conditional Controllability in Multimodal Dialogue
460. ICLR 2026From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
461. ICLR 2026From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization
462. ICLR 2026FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
463. ICLR 2026FSPO: Few-Shot Optimization of Synthetic Preferences Effectively Personalizes to Real Users
464. ICLR 2026Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective
465. ICLR 2026GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings
466. ICLR 2026Gaussian certified unlearning in high dimensions: A hypothesis testing approach
467. ICLR 2026GAVEL: Towards Rule-Based Safety through Activation Monitoring
468. ICLR 2026Gelato: Graph Edit Distance via Autoregressive Neural Combinatorial Optimization
469. ICLR 2026General Exploratory Bonus for Optimistic Exploration in RLHF
470. ICLR 2026Generative Bayesian Optimization: Generative Models as Acquisition Functions
471. ICLR 2026Generative Value Conflicts Reveal LLM Priorities
472. ICLR 2026Ghost in the Cloud: Your Geo-Distributed Large Language Models Training is Easily Manipulated
473. ICLR 2026GhostEI-Bench: Do Mobile Agent Resilience to Environmental Injection in Dynamic On-Device Environments?
474. ICLR 2026GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion Models
475. ICLR 2026GNN Explanations that do not Explain and How to find Them
476. ICLR 2026Good allocations from bad estimates
477. ICLR 2026GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing
478. ICLR 2026GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
479. ICLR 2026Gradient Intrinsic Dimensionality Alignment：Narrowing The Gap Between Low-Rank Adaptation and Full Fine-Tuning
480. ICLR 2026GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
481. ICLR 2026GradShield: Alignment Preserving Finetuning
482. ICLR 2026GraphShield: Graph-Theoretic Modeling of Network-Level Dynamics for Robust Jailbreak Detection
483. ICLR 2026Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
484. ICLR 2026GuardAlign: Robust Safety Alignment in Multimodal Large Language Models
485. ICLR 2026GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
486. ICLR 2026HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
487. ICLR 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
488. ICLR 2026HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction
489. ICLR 2026Hot PATE: Private Aggregation of Distributions for Diverse Tasks
490. ICLR 2026How Catastrophic is Your LLM? Certifying Risk in Conversation
491. ICLR 2026How Dark Patterns Manipulate Web Agents
492. ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
493. ICLR 2026Hubble: a Model Suite to Advance the Study of LLM Memorization
494. ICLR 2026Human-AI Curation Synergy: Scaling Preference Data Curation via Human-Guided AI Feedback
495. ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
496. ICLR 2026Humanline: Online Alignment as Perceptual Loss
497. ICLR 2026IA2: Alignment with ICL Activations improves Supervised Fine-Tuning
498. ICLR 2026ICPO: Provable and Practical In-Context Policy Optimization for Test-Time Scaling
499. ICLR 2026Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
500. ICLR 2026Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

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.