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

480 papers, page 8 of 10

351. NeurIPS 2026Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication
352. NeurIPS 2026Robust Domain Generalization under Divergent Marginal and Conditional Distributions
353. NeurIPS 2026Robust Policy Optimization to Prevent Catastrophic Forgetting
354. NeurIPS 2026Root Cause Analysis of Measurement and Mechanistic Anomalies
355. NeurIPS 2026Routing as a Singular Reparameterization: A Closed-Form Pushforward Prior and Exact Bayesian Complexity in a Minimal Proxy
356. NeurIPS 2026RSSA: Robust Semantic and Spatial Aligner for Collaborative Perception
357. NeurIPS 2026Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics
358. NeurIPS 2026RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control
359. NeurIPS 2026S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
360. NeurIPS 2026Safe in Its Own Words: Self-Guided Safety Alignment for Multimodal Reasoning Models
361. NeurIPS 2026Safe-PG-LQR: Provably Safe, Convergent and Optimal Model-Free Linear Quadratic Regulator with Hard Constraints
362. NeurIPS 2026Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
363. NeurIPS 2026SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMs
364. NeurIPS 2026SafePro: Generation of Safe and Functional Proteins via Cross-Task Conflict-Aware Alignment
365. NeurIPS 2026Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
366. NeurIPS 2026Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
367. NeurIPS 2026SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology
368. NeurIPS 2026SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
369. NeurIPS 2026SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards
370. NeurIPS 2026Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
371. NeurIPS 2026Scalable Neural Safety Certification via Monotonicity
372. NeurIPS 2026Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
373. NeurIPS 2026Screening Lipid Nanoparticles through Structure-Ratio Alignment
374. NeurIPS 2026SeaPilot: Mobile Agent with Self-refining Environment Alignment
375. NeurIPS 2026Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models
376. NeurIPS 2026Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
377. NeurIPS 2026Selective Safety Steering via Value-Filtered Decoding
378. NeurIPS 2026Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment
379. NeurIPS 2026SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
380. NeurIPS 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
381. NeurIPS 2026Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
382. NeurIPS 2026Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
383. NeurIPS 2026Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
384. NeurIPS 2026SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
385. NeurIPS 2026SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
386. NeurIPS 2026SoccerNarrate: Event-Grounded Streaming Soccer Commentary with Macro-Window Preference Alignment
387. NeurIPS 2026Soft Token Alignment for Cross-Lingual Reasoning
388. NeurIPS 2026Solving Stochastic Control under Multiplicative and Internal Noise via Constrained Optimization
389. NeurIPS 2026SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
390. NeurIPS 2026Sparsifying Correlation Clustering: Edge Coresets, Triangle Witnesses, and Observation Lower Bounds
391. NeurIPS 2026Spectral Alignment in Forward–Backward Representations via Temporal Abstraction
392. NeurIPS 2026Speculative Decoding Is Per-Token, Not Path
393. NeurIPS 2026Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks
394. NeurIPS 2026Sponsored Questions and How to Auction Them
395. NeurIPS 2026Stability and Diversity of Networked Self-Consuming Generative Ecosystems
396. NeurIPS 2026StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching
397. NeurIPS 2026Stage-Aware Dual Alignment for Covariate Shift in Graph Domain Adaptation
398. NeurIPS 2026SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization
399. NeurIPS 2026Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
400. NeurIPS 2026Steer2Edit: From Activation Steering to Component-Level Editing

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.