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 27 of 92

1301. ICML 2026State Space Model with Continuous Limit of HiPPO Matrix: Eigenvalue Analysis and Explicit Solution Formula
1302. ICML 2026State-Dependent Safety Failures in Multi-Turn Language Model Interaction
1303. ICML 2026Steal the Patch Size: Adversarially Manipulate Vision Language Models
1304. ICML 2026Steering at the Source: Style Modulation Heads for Robust Persona Control
1305. ICML 2026Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
1306. ICML 2026Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
1307. ICML 2026SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives
1308. ICML 2026STLA: Spatiotemporal Lookahead Alignment for Post-Training Quantization
1309. ICML 2026Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
1310. ICML 2026Structured Multi-step Jailbreaking under a Hamiltonian Generative Formulation
1311. ICML 2026Submodular Optimization for Minimal Augmentation in Robust Language Model Alignment
1312. ICML 2026Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
1313. ICML 2026Sycophancy Towards Researchers Drives Performative Misalignment
1314. ICML 2026T-GINEE: A Tensor-Based Multi-Graph Representation Learning
1315. ICML 2026T-POP: Test-Time Personalization with Online Preference Feedback
1316. ICML 2026Tackling Fake Forgetting through Uncertainty Quantification
1317. ICML 2026Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
1318. ICML 2026Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
1319. ICML 2026Task-Aware Preference Calibration for Direct Preference Optimization
1320. ICML 2026Task-Awareness Improves LLM Generations and Uncertainty
1321. ICML 2026Temporal Preference Optimization for Unsupervised Retrieval
1322. ICML 2026Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
1323. ICML 2026Test-Time Detoxification without Training or Learning Anything
1324. ICML 2026The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
1325. ICML 2026The Axiomatic Value of Regularization in AI Alignment from Human Preferences
1326. ICML 2026The benefits of full data shuffle, now with optimal I/O cost: $k$-wise independence and matrix transposition to the rescue
1327. ICML 2026The Differences Between Direct Alignment Algorithms are a Blur
1328. ICML 2026The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-Modal Divergence
1329. ICML 2026The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
1330. ICML 2026The Geometry of Updates: Fisher Alignment at Vocabulary Scale
1331. ICML 2026The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
1332. ICML 2026The Hidden Link between RLHF and Contrastive Learning
1333. ICML 2026The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
1334. ICML 2026The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
1335. ICML 2026The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
1336. ICML 2026The Pareto-optimal Trade-off between Regret and Statistical Inference in Linear Stochastic Bandits under Safety Constraints
1337. ICML 2026The Perception–Physics Paradox: Probing Scientific Alignment with TC-Bench
1338. ICML 2026The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
1339. ICML 2026The Realignment Problem: When Right becomes Wrong in LLMs
1340. ICML 2026The Sign Estimator: Preference Modeling for LLM Alignment under Heterogeneity
1341. ICML 2026The Theory and Practice of MAP Inference over Non-Convex Constraints
1342. ICML 2026The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
1343. ICML 2026Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
1344. ICML 2026Theoretical Challenges in Learning for Branch-and-Cut
1345. ICML 2026Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
1346. ICML 2026Threshold-Guided Optimization for Visual Generative Models
1347. ICML 2026Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
1348. ICML 2026Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
1349. ICML 2026TMD-Bench: A Multi-Level Evaluation Paradigm for Music–Dance Co-Generation
1350. ICML 2026TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

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.