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

623 papers, page 11 of 13

501. ICLR 2026Skirting Additive Error Lower Bounds for Private Turnstile Streams
502. ICLR 2026sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals
503. ICLR 2026SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
504. ICLR 2026SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
505. ICLR 2026SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
506. ICLR 2026SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
507. ICLR 2026Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
508. ICLR 2026SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
509. ICLR 2026SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
510. ICLR 2026Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
511. ICLR 2026SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
512. ICLR 2026SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
513. ICLR 2026Spilled Energy in Large Language Models
514. ICLR 2026Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
515. ICLR 2026ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
516. ICLR 2026Stable and Scalable Deep Predictive Coding Networks with Meta Prediction Errors
517. ICLR 2026Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
518. ICLR 2026STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model
519. ICLR 2026Statistical Guarantees in the Search for Less Discriminatory Algorithms
520. ICLR 2026Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
521. ICLR 2026Steering Evaluation-Aware Language Models To Act Like They Are Deployed
522. ICLR 2026Steering Language Models with Weight Arithmetic
523. ICLR 2026Steering MoE LLMs via Expert (De)Activation
524. ICLR 2026Steering the Herd: A Framework for LLM-based Control of Social Learning
525. ICLR 2026Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
526. ICLR 2026Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
527. ICLR 2026Strategic Obfuscation of Deceptive Reasoning in Language Models
528. ICLR 2026Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance
529. ICLR 2026Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
530. ICLR 2026Superficial Safety Alignment Hypothesis
531. ICLR 2026Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent Space
532. ICLR 2026Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
533. ICLR 2026SYNC: Measuring and Advancing Synthesizability in Structure-Based Drug Design
534. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
535. ICLR 2026t-SNE Exaggerates Clusters, Provably
536. ICLR 2026TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
537. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
538. ICLR 2026Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
539. ICLR 2026Temporal Generalization: A Reality Check
540. ICLR 2026Test-Time Alignment for Large Language Models via Textual Model Predictive Control
541. ICLR 2026Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP
542. ICLR 2026Text2Grad: Reinforcement Learning from Natural Language Feedback
543. ICLR 2026The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
544. ICLR 2026The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
545. ICLR 2026The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
546. ICLR 2026The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
547. ICLR 2026The Geometry and Topology of Circuits: the Manifolds of Modular Addition
548. ICLR 2026The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
549. ICLR 2026The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding
550. ICLR 2026The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's Algorithm

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.