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

455 papers, page 9 of 10

401. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
402. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
403. NeurIPS 2025The Indra Representation Hypothesis
404. NeurIPS 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
405. NeurIPS 2025The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education
406. NeurIPS 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
407. NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
408. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
409. NeurIPS 2025Thresholds for sensitive optimality and Blackwell optimality in stochastic games
410. NeurIPS 2025Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting
411. NeurIPS 2025Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
412. NeurIPS 2025Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
413. NeurIPS 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
414. NeurIPS 2025Token-Level Self-Play with Importance-Aware Guidance for Large Language Models
415. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
416. NeurIPS 2025Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
417. NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
418. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
419. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
420. NeurIPS 2025Training-Free Safe Denoisers for Safe Use of Diffusion Models
421. NeurIPS 2025Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
422. NeurIPS 2025Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
423. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
424. NeurIPS 2025Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
425. NeurIPS 2025U-REPA: Aligning Diffusion U-Nets to ViTs
426. NeurIPS 2025UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation
427. NeurIPS 2025Understanding and Rectifying Safety Perception Distortion in VLMs
428. NeurIPS 2025Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
429. NeurIPS 2025Unifying Reconstruction and Density Estimation via Invertible Contraction Mapping in One-Class Classification
430. NeurIPS 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
431. NeurIPS 2025Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data
432. NeurIPS 2025Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
433. NeurIPS 2025Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model
434. NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
435. NeurIPS 2025Value Gradient Guidance for Flow Matching Alignment
436. NeurIPS 2025Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation
437. NeurIPS 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
438. NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
439. NeurIPS 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models
440. NeurIPS 2025VLMs can Aggregate Scattered Training Patches
441. NeurIPS 2025VMDT: Decoding the Trustworthiness of Video Foundation Models
442. NeurIPS 2025VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information
443. NeurIPS 2025Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
444. NeurIPS 2025Weak-to-Strong Generalization under Distribution Shifts
445. NeurIPS 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability
446. NeurIPS 2025What Makes a Reward Model a Good Teacher? An Optimization Perspective
447. NeurIPS 2025What Matters in Data for DPO?
448. NeurIPS 2025When and how can inexact generative models still sample from the data manifold?
449. NeurIPS 2025When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
450. NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

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.