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 31 of 38

1501. NeurIPS 2026CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
1502. NeurIPS 2026CRAFT: Conflict-Resolved Aggregation for Federated Training
1503. NeurIPS 2026Cross-Architecture Transferability is Width-Confounded:Diagnosis and Subspace Correction
1504. NeurIPS 2026DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment
1505. NeurIPS 2026DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
1506. NeurIPS 2026DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy Alignment
1507. NeurIPS 2026DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
1508. NeurIPS 2026DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
1509. NeurIPS 2026Debiased DPO for Diffusion Models
1510. NeurIPS 2026Decomposed Representations Mitigate the Alignment–Specificity Trade-off in Multi-Omics
1511. NeurIPS 2026Decomposing and Reshaping Scaling Laws through Token Learning Times
1512. NeurIPS 2026Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
1513. NeurIPS 2026Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation
1514. NeurIPS 2026Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval
1515. NeurIPS 2026Decoupling Label Shift and Surrogate Gradient Errors for Robust Federated Spiking Neural Networks
1516. NeurIPS 2026Deep Minds and Shallow Probes
1517. NeurIPS 2026Denoising Implicit Variational Inference
1518. NeurIPS 2026Dense Cross-Tokenizer Distillation via Semantic Optimal Local Alignment
1519. NeurIPS 2026Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
1520. NeurIPS 2026Differentiable Knapsack and Top-k Operators via Dynamic Programming
1521. NeurIPS 2026Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization
1522. NeurIPS 2026Disentangling the Good From the Bad: Quantization-Induced Flips Are Not Random
1523. NeurIPS 2026Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
1524. NeurIPS 2026Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
1525. NeurIPS 2026Distributionally Robust Listwise Preference Optimization
1526. NeurIPS 2026Distributionally Robust Token Optimization in RLHF
1527. NeurIPS 2026Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
1528. NeurIPS 2026Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
1529. NeurIPS 2026DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
1530. NeurIPS 2026Does Weight Decay Enhance Training Stability?
1531. NeurIPS 2026DrPO: Drifting Preference Optimization for One-Step Generative Models
1532. NeurIPS 2026E-GEO: A Testbed for Generative Engine Optimization in E-Commerce
1533. NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
1534. NeurIPS 2026Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
1535. NeurIPS 2026Emergence, Retention and Mitigation of Ill-conditioning due to Basis Lifting in KANs
1536. NeurIPS 2026Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
1537. NeurIPS 2026Enhancing Speech Large Language Models through Reinforced Behavior Alignment
1538. NeurIPS 2026EpiPivot: Learning to Control the Simplex Method under Epistemic Uncertainty
1539. NeurIPS 2026EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment
1540. NeurIPS 2026EvalAwareBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
1541. NeurIPS 2026Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage
1542. NeurIPS 2026Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
1543. NeurIPS 2026Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
1544. NeurIPS 2026Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
1545. NeurIPS 2026Explaining and Preventing Alignment Collapse in Iterative RLHF
1546. NeurIPS 2026Explanation Multiplicity in SHAP: Characterization and Assessment
1547. NeurIPS 2026Fail-Closed Alignment for Large Language Models
1548. NeurIPS 2026Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
1549. NeurIPS 2026Fair Range k-Supplier Clustering in Offline and Streaming Models
1550. NeurIPS 2026FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators

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.