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

600 papers, page 6 of 12

251. CVPR 2025Can Text-to-Video Generation help Video-Language Alignment?
252. CVPR 2025CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
253. CVPR 2025Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment
254. CVPR 2025Chebyshev Attention Depth Permutation Texture Network with Latent Texture Attribute Loss
255. CVPR 2025ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
256. CVPR 2025Continual SFT Matches Multimodal RLHF with Negative Supervision
257. CVPR 2025Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
258. CVPR 2025CrossOver: 3D Scene Cross-Modal Alignment
259. CVPR 2025Curriculum Direct Preference Optimization for Diffusion and Consistency Models
260. CVPR 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
261. CVPR 2025Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
262. CVPR 2025Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
263. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
264. CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
265. CVPR 2025Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality
266. CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
267. CVPR 2025Doppelgangers and Adversarial Vulnerability
268. CVPR 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
269. CVPR 2025EBS-EKF: Accurate and High Frequency Event-based Star Tracking
270. CVPR 2025EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
271. CVPR 2025Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework
272. CVPR 2025Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation
273. CVPR 2025Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces
274. CVPR 2025EventPSR: Surface Normal and Reflectance Estimation from Photometric Stereo Using an Event Camera
275. CVPR 2025Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
276. CVPR 2025Flexible Group Count Enables Hassle-Free Structured Pruning
277. CVPR 2025Font-Agent: Enhancing Font Understanding with Large Language Models
278. CVPR 2025Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution
279. CVPR 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
280. CVPR 2025HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
281. CVPR 2025Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching
282. CVPR 2025HOT: Hadamard-based Optimized Training
283. CVPR 2025Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
284. CVPR 2025HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
285. CVPR 2025Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
286. CVPR 2025Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
287. CVPR 2025Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity
288. CVPR 2025Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning
289. CVPR 2025Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models
290. CVPR 2025InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
291. CVPR 2025iSegMan: Interactive Segment-and-Manipulate 3D Gaussians
292. CVPR 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learning
293. CVPR 2025JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems
294. CVPR 2025Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning
295. CVPR 2025LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation
296. CVPR 2025Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model
297. CVPR 2025Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References
298. CVPR 2025Let's Verify and Reinforce Image Generation Step by Step
299. CVPR 2025Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
300. CVPR 2025MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

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.