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 6 of 92

251. ICLR 2026Aligning Deep Implicit Preferences by Learning to Reason Defensively
252. ICLR 2026Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
253. ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
254. ICLR 2026Alignment-Weighted DPO: A principled reasoning approach to improve alignment
255. ICLR 2026AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
256. ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
257. ICLR 2026All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
258. ICLR 2026AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
259. ICLR 2026AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
260. ICLR 2026Annotation-Efficient Honesty Alignment via Confidence Elicitation and Calibration
261. ICLR 2026Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
262. ICLR 2026Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
263. ICLR 2026Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
264. ICLR 2026Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
265. ICLR 2026Are Deep Speech Denoising Models Robust to Adversarial Noise?
266. ICLR 2026ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
267. ICLR 2026ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
268. ICLR 2026ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
269. ICLR 2026ASIDE: Architectural Separation of Instructions and Data in Language Models
270. ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
271. ICLR 2026Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
272. ICLR 2026Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
273. ICLR 2026Attention Smoothing Is All You Need For Unlearning
274. ICLR 2026AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion Models
275. ICLR 2026AttTok: Marrying Attribute Tokens with Generative Pre-trained Vision-Language Models towards Medical Image Understanding
276. ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
277. ICLR 2026Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
278. ICLR 2026Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies
279. ICLR 2026AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
280. ICLR 2026Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
281. ICLR 2026Balancing the Experts: Unlocking LoRA-MoE for GRPO via Mechanism-Aware Rewards
282. ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
283. ICLR 2026BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
284. ICLR 2026BaseReward: A Strong Baseline for Multimodal Reward Model
285. ICLR 2026Batch and Sequential Unlearning for Neural Networks
286. ICLR 2026Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
287. ICLR 2026Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
288. ICLR 2026Benchmarking Open-ended Segmentation
289. ICLR 2026Benchmarking Overton Pluralism in LLMs
290. ICLR 2026Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
291. ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
292. ICLR 2026Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
293. ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
294. ICLR 2026Beyond Pairwise: Empowering LLM Alignment With (Ranked) Choice Modeling
295. ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
296. ICLR 2026Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
297. ICLR 2026Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
298. ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
299. ICLR 2026Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
300. ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses

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.