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 16 of 92

751. ICLR 2026Steering MoE LLMs via Expert (De)Activation
752. ICLR 2026Steering the Herd: A Framework for LLM-based Control of Social Learning
753. ICLR 2026Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
754. ICLR 2026Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
755. ICLR 2026Strategic Obfuscation of Deceptive Reasoning in Language Models
756. ICLR 2026Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance
757. ICLR 2026Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
758. ICLR 2026Superficial Safety Alignment Hypothesis
759. ICLR 2026Supporting High-Stakes Decision Making Through Interactive Preference Elicitation in the Latent Space
760. ICLR 2026Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
761. ICLR 2026SYNC: Measuring and Advancing Synthesizability in Structure-Based Drug Design
762. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
763. ICLR 2026t-SNE Exaggerates Clusters, Provably
764. ICLR 2026TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
765. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
766. ICLR 2026Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
767. ICLR 2026Temporal Generalization: A Reality Check
768. ICLR 2026Test-Time Alignment for Large Language Models via Textual Model Predictive Control
769. ICLR 2026Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP
770. ICLR 2026Text2Grad: Reinforcement Learning from Natural Language Feedback
771. ICLR 2026The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
772. ICLR 2026The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
773. ICLR 2026The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
774. ICLR 2026The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
775. ICLR 2026The Geometry and Topology of Circuits: the Manifolds of Modular Addition
776. ICLR 2026The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
777. ICLR 2026The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding
778. ICLR 2026The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's Algorithm
779. ICLR 2026The Mind's Transformer: Computational Neuroanatomy of LLM-Brain Alignment
780. ICLR 2026THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCE
781. ICLR 2026Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation Detection
782. ICLR 2026TileLang: Bridge Programmability and Performance in Modern Neural Kernels
783. ICLR 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
784. ICLR 2026Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
785. ICLR 2026Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
786. ICLR 2026Token-Importance Guided Direct Preference Optimization
787. ICLR 2026Token-level Data Selection for Safe LLM Fine-tuning
788. ICLR 2026Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
789. ICLR 2026Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
790. ICLR 2026Towards Better Optimization For Listwise Preference in Diffusion Models
791. ICLR 2026Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
792. ICLR 2026Towards Learned Optimization Free Lunch
793. ICLR 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
794. ICLR 2026Towards Persistent Noise-Tolerant Active Learning of Regular Languages with Class Query
795. ICLR 2026Towards Personalized Deep Research: Benchmarks and Evaluations
796. ICLR 2026Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without Disclosure
797. ICLR 2026Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
798. ICLR 2026Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
799. ICLR 2026Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model
800. ICLR 2026Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer

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.