| Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques | Agents | Juho Kim +1 | May 14, 2026 | — |
| Artificial Intelligence-Assistant Cardiotocography: Unified Model for Signal Reconstruction, Fetal Heart Rate Analysis, and Variability Assessment | Science & bio | Xiaohua Wang +4 | May 14, 2026 | — |
| SurF: A Generative Model for Multivariate Irregular Time Series Forecasting | Data & benchmarks | Mohammad R. Rezaei +2 | May 13, 2026 | — |
| Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization | Code | Irene Aldridge | May 13, 2026 | — |
| Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation | Efficiency & systems | Haoran Li +6 | May 13, 2026 | — |
| Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo | Data & benchmarks | Ejaaz Merali +4 | May 13, 2026 | — |
| Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling | Code | Gaurav Rudravaram +19 | May 13, 2026 | — |
| Causal Learning with the Invariance Principle | Efficiency & systems | Francesco Montagna +1 | May 13, 2026 | — |
| Beyond Explained Variance: A Cautionary Tale of PCA | Vision & multimodal | Gionni Marchetti | May 13, 2026 | — |
| Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation | Code | Lilin Zhang +4 | May 13, 2026 | — |
| Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications | Agents | Maxwell Standen +2 | May 13, 2026 | — |
| Covariance-aware sampling for Diffusion Models | Image & video gen | Andrea Schioppa +1 | May 13, 2026 | — |
| Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels | Code | Yusuke Hayashi | May 13, 2026 | — |
| Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation | Safety & alignment | Runlong Xie +1 | May 13, 2026 | — |
| Protocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence | Code | Jun He +1 | May 13, 2026 | — |
| Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering | Vision & multimodal | Feijiang Li +5 | May 13, 2026 | — |
| IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning | Efficiency & systems | Vahid Balazadeh +4 | May 13, 2026 | — |
| REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations | Code | Buyun Liang +8 | May 12, 2026 | — |
| Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage | Speech & audio | Fusheng Luo +1 | May 12, 2026 | — |
| Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery | Robotics | Marios Papamichalis +1 | May 12, 2026 | — |
| Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting | Theory | Laura Lützow +4 | May 12, 2026 | — |
| Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods | Theory | Roozbeh Razavi-Far +8 | May 12, 2026 | — |
| Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS | Data & benchmarks | Gaspard Berthelier +6 | May 12, 2026 | — |
| Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates | Safety & alignment | Patryk Rygiel +4 | May 12, 2026 | — |
| Variance-aware Reward Modeling with Anchor Guidance | Reinforcement learning | Shuxing Fang +3 | May 12, 2026 | — |
| Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media | Safety & alignment | Martin Hohmann | May 12, 2026 | — |
| Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling | Code | Thor Klamt +2 | May 12, 2026 | — |
| Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation | Safety & alignment | Cristian Morasso +3 | May 12, 2026 | — |
| Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning | Data & benchmarks | Chi Zhang +5 | May 12, 2026 | — |
| EpiCastBench: Datasets and Benchmarks for Multivariate Epidemic Forecasting | Code | Madhurima Panja +4 | May 12, 2026 | — |
| A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods | Theory | Shota Saito +5 | May 12, 2026 | — |
| VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck | Vision & multimodal | Aryan Gondkar +2 | May 12, 2026 | — |
| Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting | Reinforcement learning | Cheng Wang +3 | May 12, 2026 | — |
| Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses | Reinforcement learning | Kihyun Yu +2 | May 12, 2026 | — |
| Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies | Image & video gen | Takuro Kutsuna +3 | May 12, 2026 | — |
| Physics-Grounded Adversarial Stain Augmentation with Calibrated Coverage Guarantees | Science & bio | Mingi Hong | May 12, 2026 | — |
| Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe | Agents | Riad Ahmed | May 12, 2026 | — |
| Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors | Vision & multimodal | Wen-Ting Wang +3 | May 12, 2026 | — |
| LPDP: Inference-Time Reward Control for Variable-Length DNA Generation with Edit Flows | Code | Jeongchan Kim +2 | May 12, 2026 | — |
| Variational Linear Attention: Stable Associative Memory for Long-Context Transformers | Robotics | Vishal Pandey +1 | May 11, 2026 | — |
| Adversarial SQL Injection Generation with LLM-Based Architectures | Code | Ali Karakoc +1 | May 11, 2026 | — |
| Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs | Vision & multimodal | Youssef Zaazou +1 | May 11, 2026 | — |
| Variational Inference for Lévy Process-Driven SDEs via Neural Tilting | Safety & alignment | Yaman Kindap +4 | May 11, 2026 | — |
| Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis | Agents | Richie Yeung +2 | May 11, 2026 | — |
| Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium | Vision & multimodal | Qingxin Xiao +4 | May 11, 2026 | — |
| A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables | Speech & audio | Zheng Li +5 | May 11, 2026 | — |
| Where do aspectual variants of light verb constructions belong? | Other | Aggeliki Fotopoulou +2 | May 11, 2026 | — |
| Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes | Data & benchmarks | Yasmine Abu-Haeyeh +3 | May 11, 2026 | — |
| Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition | LLMs & reasoning | Haoren Xu +1 | May 11, 2026 | — |
| DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection | Vision & multimodal | Chaeyoung Lee +2 | May 11, 2026 | — |
| PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation | Agents | Ahmet Onur Akman +1 | May 11, 2026 | — |
| Nearly-Optimal Algorithm for Adversarial Kernelized Bandits | Theory | Shogo Iwazaki | May 11, 2026 | — |
| Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization | Data & benchmarks | Jinping Wang +3 | May 11, 2026 | — |
| One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification | Data & benchmarks | Mengzhou Gao +2 | May 11, 2026 | — |
| Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables | Agents | Damon McMillan | May 11, 2026 | — |
| Total Generalized Variation regularization closes the gap between neural-eld and classical methods in seismic travel-time tomography | Safety & alignment | Isao Kurosawa | May 11, 2026 | — |
| Quantum Circuit Simulation of Compartmental Drug Dynamics: Leveraging Variational Algorithms for Nonlinear Mixed-Effects Population Pharmacokinetics | Safety & alignment | Isshaan Singh +1 | May 10, 2026 | — |
| S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes | Other | Albert Heruth | May 10, 2026 | — |
| Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness | Reinforcement learning | Zizhao Chen +3 | May 10, 2026 | — |
| Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow | Theory | Lénaïc Chizat +3 | May 10, 2026 | — |
| On Variance Reduction in Learning Mean Flows | Image & video gen | Juanwu Lu +1 | May 10, 2026 | — |
| On Characterizing Learnability for Adversarial Noisy Bandits | Other | Steve Hanneke +1 | May 9, 2026 | — |
| A Quantum Inspired Variational Kernel and Explainable AI Framework for Cross Region Solar and Wind Energy Forecasting | Code | Pavan Manjunath +1 | May 9, 2026 | — |
| GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives | Vision & multimodal | Alexandre Le Mercier +2 | May 9, 2026 | — |
| Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-wise Adaptive Regularization Approach | Vision & multimodal | Hira Nasir +4 | May 9, 2026 | — |
| Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning | Efficiency & systems | Chen Wang +3 | May 9, 2026 | — |
| Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction | Data & benchmarks | Zhirayr Tovmasyan +2 | May 9, 2026 | — |
| AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines | Efficiency & systems | Tingxi Li +5 | May 9, 2026 | — |
| METBRA25Y: Brazil Surface Meteorology Archive with Harmonized Variables and Quality Control | Data & benchmarks | Matheus Lima Castro +2 | May 9, 2026 | — |
| PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks | Vision & multimodal | Zhenxin Ai +1 | May 9, 2026 | — |
| Improving Generative Adversarial Networks with Self-Distillation | Image & video gen | Antoni Nowinowski +1 | May 9, 2026 | — |
| Multivariate Financial Forecasting using the Chronos Time Series Foundation Models | Vision & multimodal | Sanjiv R Das +2 | May 8, 2026 | — |
| TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers | Image & video gen | Daniel Wesego +1 | May 8, 2026 | — |
| LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight | Robotics | Lennart Wachowiak +3 | May 8, 2026 | — |
| KL for a KL: On-Policy Distillation with Control Variate Baseline | Safety & alignment | Minjae Oh +4 | May 8, 2026 | — |
| Exact Regular-Constrained Variable-Order Markov Generation via Sparse Context-State Belief Propagation | Efficiency & systems | François Pachet | May 8, 2026 | — |
| Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models | Efficiency & systems | Boyu Shi +5 | May 8, 2026 | — |
| Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns | Data & benchmarks | Guolin Yin +3 | May 8, 2026 | — |
| Disagreement-Regularized Importance Sampling for Adversarial Label Corruption | Safety & alignment | Csongor Horváth +2 | May 8, 2026 | — |
| On the Invariance and Generality of Neural Scaling Laws | Speech & audio | Xing Han +3 | May 8, 2026 | — |
| SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching | Efficiency & systems | Hippolyte Labarrière +3 | May 8, 2026 | — |
| Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs | Vision & multimodal | Hao Wang +4 | May 8, 2026 | — |
| What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies | Efficiency & systems | Fan Zhang +2 | May 8, 2026 | — |
| Diagnosing Spectral Ceilings in Equivariant Neural Force Fields | Science & bio | Hyunmog Kim | May 8, 2026 | — |
| Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative | Code | Sibayan Mitra +1 | May 8, 2026 | — |
| Sample Complexity of Stochastic Optimization with Integer Variables | Theory | Hongyu Cheng +3 | May 8, 2026 | — |
| Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents | Vision & multimodal | Deeraj S K +3 | May 8, 2026 | — |
| PolarAdamW: Disentangling Spectral Control and Schur Gauge-Equivariance in Matrix Optimisation | LLMs & reasoning | Haozhou Zhang | May 8, 2026 | — |
| GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations | Safety & alignment | Jyotika Singh +13 | May 8, 2026 | — |
| BGM-IV: an AI-powered Bayesian generative modeling approach for instrumental variable analysis | Code | Guyue Luo +1 | May 7, 2026 | — |
| Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization | Agents | Da Long +5 | May 7, 2026 | — |
| Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks | Agents | Saisai Hu | May 7, 2026 | — |
| Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics | Code | Shane Cairns +4 | May 7, 2026 | — |
| Hybrid Quantum-Classical GANs for the Generation of Adversarial Network Flows | Image & video gen | Prateek Paudel +3 | May 7, 2026 | — |
| The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity | Efficiency & systems | Siquan Li +3 | May 7, 2026 | — |
| DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments | Efficiency & systems | Kateryna Husar +1 | May 7, 2026 | — |
| Operator-Guided Invariance Learning for Continuous Reinforcement Learning | Image & video gen | Zuyuan Zhang +2 | May 7, 2026 | — |
| Dynamic Controlled Variables Based Dynamic Self-Optimizing Control | Theory | Chenchen Zhou +5 | May 7, 2026 | — |
| Invariant-Based Diagnostics for Graph Benchmarks | Efficiency & systems | Richard von Moos +2 | May 7, 2026 | — |
| Invariant Features in Language Models: Geometric Characterization and Model Attribution | Efficiency & systems | Agnibh Dasgupta +2 | May 7, 2026 | — |