| Neural-Actuarial Longevity Forecasting: Anchoring LSTMs for Explainable Risk Management | Safety & alignment | Davide Rindori | May 7, 2026 | — |
| Covariate Balancing and Riesz Regression Should Be Guided by the Neyman Orthogonal Score in Debiased Machine Learning | Safety & alignment | Masahiro Kato | May 7, 2026 | — |
| Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation | Speech & audio | Ana Leticia Garcez Vicente +2 | May 7, 2026 | — |
| Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations | Image & video gen | Yuan Du +2 | May 7, 2026 | — |
| Eliciting associations between clinical variables from LLMs via comparison questions across populations | Safety & alignment | Fabian Kabus +5 | May 7, 2026 | — |
| Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation | Vision & multimodal | Maximilian Maurer +2 | May 7, 2026 | — |
| Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks | Vision & multimodal | Guanmeng Xian +2 | May 7, 2026 | — |
| Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation | Vision & multimodal | Bowen Zheng +4 | May 7, 2026 | — |
| Constrained Contextual Bandits with Adversarial Contexts | Other | Dhruv Sarkar +1 | May 7, 2026 | — |
| Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers | Image & video gen | Pengqi Lu | May 7, 2026 | — |
| Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges | Agents | Shihao Weng +2 | May 7, 2026 | — |
| Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation | Safety & alignment | Huizi Cui +4 | May 7, 2026 | — |
| RVPO: Risk-Sensitive Alignment via Variance Regularization | Reinforcement learning | Ivan Montero +2 | May 7, 2026 | — |
| Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows | Image & video gen | Yu Wang +1 | May 7, 2026 | — |
| A Simple State Space Model Excels at Multivariate Time Series Classification | Data & benchmarks | Hassan Saadatmand +3 | May 7, 2026 | — |
| Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation | Data & benchmarks | Tran Gia Bao Ngo +4 | May 7, 2026 | — |
| Permutation-preserving Functions and Neural Vecchia Covariance Kernels | Efficiency & systems | Jian Cao +2 | May 6, 2026 | — |
| Information Theoretic Adversarial Training of Large Language Models | Safety & alignment | Yiwei Zhang +5 | May 6, 2026 | — |
| Transformed Latent Variable Multi-Output Gaussian Processes | Efficiency & systems | Xiaoyu Jiang +4 | May 6, 2026 | — |
| Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series | Data & benchmarks | Ruichao Guo +5 | May 6, 2026 | — |
| Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift | Data & benchmarks | Jonathan R. Landers | May 6, 2026 | — |
| Learngene Search Across Multiple Datasets for Building Variable-Sized Models | Vision & multimodal | Boyu Shi +5 | May 6, 2026 | — |
| Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks | Vision & multimodal | Zhenan Shao +4 | May 6, 2026 | — |
| Covariance-Aware Goodness for Scalable Forward-Forward Learning | Safety & alignment | Xiaoyi Jiang +2 | May 5, 2026 | — |
| Laundering AI Authority with Adversarial Examples | Robotics | Jie Zhang +3 | May 5, 2026 | — |
| Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising | LLMs & reasoning | Youssef Saied +1 | May 5, 2026 | — |
| On Computing Total Variation Distance Between Mixtures of Product Distributions | Other | Weiming Feng +3 | May 5, 2026 | — |
| Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification | Efficiency & systems | Nan Feng +1 | May 5, 2026 | — |
| Adversarial Effects on Expressibility and Trainability in Distributed Variational Quantum Algorithms | Safety & alignment | Abhishek Sadhu +1 | May 5, 2026 | — |
| Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks | Science & bio | Diego Marcondes | May 5, 2026 | — |
| GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains | Image & video gen | James Rowbottom +5 | May 5, 2026 | — |
| Real-Time Evaluation of Autonomous Systems under Adversarial Attacks | Reinforcement learning | Adithya Mohan +3 | May 5, 2026 | — |
| Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits | Agents | Yu-Ting Lee +2 | May 5, 2026 | — |
| TsallisPGD: Adaptive Gradient Weighting for Adversarial Attacks on Semantic Segmentation | Vision & multimodal | Alexander Matyasko +3 | May 5, 2026 | — |
| A Fast Model Counting Algorithm for Two-Variable Logic with Counting and Modulo Counting Quantifiers | Efficiency & systems | Shixin Sun +4 | May 5, 2026 | — |
| Distributed Learning with Adversarial Gradient Perturbations | Theory | Nawapon Sangsiri +1 | May 5, 2026 | — |
| Augmented Equivariant Mesh Networks for Anatomical Segmentation | Vision & multimodal | Daniel Saragih | May 4, 2026 | — |
| PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization | Agents | Mingshuo Liu +2 | May 4, 2026 | — |
| Distributed Deep Variational Approach for Privacy-preserving Data Release | Efficiency & systems | Zahir Alsulaimawi +1 | May 4, 2026 | — |
| ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration | Vision & multimodal | Ruofeng Yang +2 | May 4, 2026 | — |
| LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models | Image & video gen | Fengqi Zhu +10 | May 25, 2025 | — |
| ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection | Speech & audio | Thomas Hartvigsen +5 | Mar 17, 2022 | — |
| SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition | Vision & multimodal | Kaiyu Yang +2 | Aug 7, 2019 | — |
| WinoGrande: An Adversarial Winograd Schema Challenge at Scale | Safety & alignment | Keisuke Sakaguchi +3 | Jul 24, 2019 | — |