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 50 of 92

2451. ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
2452. ICLR 2025Towards hyperparameter-free optimization with differential privacy
2453. ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
2454. ICLR 2025Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
2455. ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
2456. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
2457. ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
2458. ICLR 2025Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
2459. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
2460. ICLR 2025Training-Free Diffusion Model Alignment with Sampling Demons
2461. ICLR 2025Training-free LLM-generated Text Detection by Mining Token Probability Sequences
2462. ICLR 2025Transformers Learn Low Sensitivity Functions: Investigations and Implications
2463. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
2464. ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
2465. ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
2466. ICLR 2025Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
2467. ICLR 2025Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
2468. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
2469. ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
2470. ICLR 2025UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
2471. ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
2472. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
2473. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
2474. ICLR 2025Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
2475. ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
2476. ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
2477. ICLR 2025Variational Best-of-N Alignment
2478. ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
2479. ICLR 2025VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
2480. ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
2481. ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
2482. ICLR 2025Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
2483. ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
2484. ICLR 2025Wasserstein Distances, Neuronal Entanglement, and Sparsity
2485. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
2486. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
2487. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
2488. ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
2489. ICLR 2025Your Weak LLM is Secretly a Strong Teacher for Alignment
2490. ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
2491. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
2492. ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
2493. ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
2494. ICML 2025A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
2495. ICML 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
2496. ICML 2025A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
2497. ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
2498. ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
2499. ICML 2025Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
2500. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models

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.