| KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks | Code | Lorenz K. Muller +5 | Jun 2, 2026 | 59 |
| SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations | Agents | Taewon Yun +5 | Jun 4, 2026 | 51 |
| Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning | Vision & multimodal | Shijie Li +9 | Jul 1, 2026 | 27 |
| BadWorld: Adversarial Attacks on World Models | Image & video gen | Linghui Shen +2 | Jun 15, 2026 | 18 |
| Variable-Width Transformers | Efficiency & systems | Zhaofeng Wu +5 | Jun 16, 2026 | 15 |
| AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation | Image & video gen | Haobo Li +8 | Jun 2, 2026 | 14 |
| Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution | Image & video gen | Zixin Jessie Chen +6 | May 25, 2026 | 13 |
| Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models | Speech & audio | Malikeh Ehghaghi +3 | Jun 9, 2026 | 9 |
| GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks | Robotics | Kaiyuan Chen +23 | Jul 6, 2026 | 5 |
| Adaptive Volumetric Mechanical Property Fields Invariant to Resolution | Efficiency & systems | Rishit Dagli +6 | Jun 16, 2026 | 5 |
| Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates | Safety & alignment | Paiheng Xu +2 | Jun 2, 2026 | 5 |
| Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence | Vision & multimodal | Prashant C. Raju | Jun 28, 2026 | 4 |
| MeshFlow: Mesh Generation with Equivariant Flow Matching | Image & video gen | Qi Sun +8 | Jun 22, 2026 | 3 |
| PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection | Vision & multimodal | Md. Shakhoyat Rahman Shujon +4 | Jul 6, 2026 | 1 |
| Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops | Agents | Ziqian Zhong +5 | Jun 8, 2026 | 1 |
| The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure | Data & benchmarks | Yubo Li +2 | May 27, 2026 | 1 |
| Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting | Speech & audio | Shuang Liang +6 | May 26, 2026 | — |
| Wasserstein Contraction of Coordinate Ascent Variational Inference | Efficiency & systems | Rocco Caprio +2 | May 28, 2026 | — |
| Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables | Code | Masaaki Imaizumi +3 | May 28, 2026 | — |
| MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference | Code | Kexin Chu +2 | May 28, 2026 | — |
| Improving Adversarial Robustness of Attribution via Implicit Regularization | Data & benchmarks | Amir Mehrpanah +2 | May 28, 2026 | — |
| Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning | Safety & alignment | Zhenghao Herbert Zhou +2 | May 28, 2026 | — |
| MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables | Speech & audio | Sung-Lin Yeh +8 | May 28, 2026 | — |
| Harnessing non-adversarial robustness in large language models | Safety & alignment | Qinghua Zhou +8 | May 28, 2026 | — |
| Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption | Other | Santanu Das +2 | May 28, 2026 | — |
| SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing | Safety & alignment | Almene De Meran Meguimtsop +2 | May 28, 2026 | — |
| Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference | Efficiency & systems | Mykola Lukashchuk +6 | May 28, 2026 | — |
| Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning | Other | Kun Ren +2 | May 28, 2026 | — |
| FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks | Data & benchmarks | Nishal Thomas +1 | May 27, 2026 | — |
| Learning Robust and Task-Invariant Functional Representation from fMRI through Siamese Self-Supervised Learning | Efficiency & systems | Jiyao Wang +6 | May 27, 2026 | — |
| Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization | Efficiency & systems | Beiduo Chen +5 | May 27, 2026 | — |
| Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields | Code | Julien Lalanne +5 | May 27, 2026 | — |
| Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration | Code | Haonan Wen +2 | May 27, 2026 | — |
| Quantum-Enhanced Adversarial Robustness in Artificial Intelligence | Safety & alignment | Jaydip Sen | May 27, 2026 | — |
| Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation | Reinforcement learning | Wonyoung Kim +3 | May 27, 2026 | — |
| Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector | Vision & multimodal | Junhao Wei +11 | May 27, 2026 | — |
| SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning | Robotics | Jiachen Qian | May 27, 2026 | — |
| Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction | Reinforcement learning | Zehan Li +4 | May 27, 2026 | — |
| Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security | Vision & multimodal | Xiang Fang +1 | May 27, 2026 | — |
| Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems | Agents | Seunghyuk Cho +6 | May 27, 2026 | — |
| Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection | Vision & multimodal | Niccolò Ferrari +2 | May 26, 2026 | — |
| Structure over Pixels: Learning Variable-Length Visual Programs | Vision & multimodal | Piotr Wyrwiński +2 | May 26, 2026 | — |
| On the Equivariant Learning of the $Q$-tensor Order Parameter | Data & benchmarks | Julia Navarro +1 | May 26, 2026 | — |
| How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks | Vision & multimodal | Teodor-Mihai Stupariu +1 | May 26, 2026 | — |
| Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling | Safety & alignment | Yiding Liu +7 | May 26, 2026 | — |
| Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation | Vision & multimodal | Khayyam Nosrati +4 | May 26, 2026 | — |
| Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher | Robotics | Zhenglin Wan +7 | May 26, 2026 | — |
| ConVer: Using Contracts and Loop Invariant Synthesis for Scalable Formal Software Verification | Efficiency & systems | Muhammad A. A. Pirzada +4 | May 26, 2026 | — |
| When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study | Theory | Jun Yan +6 | May 26, 2026 | — |
| Resource-Constrained Affect Modelling via Variance Regularisation Pruning | Efficiency & systems | Kosmas Pinitas +1 | May 26, 2026 | — |
| Neural Autoregressive Control Variates for the Quantum Monte Carlo Sign Problem | Safety & alignment | Bei Qiao +1 | May 26, 2026 | — |
| EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation | Agents | Yunbo Long +4 | May 26, 2026 | — |
| Ratio-Variance Regularized Policy Optimization | Robotics | Yu Luo +7 | May 26, 2026 | — |
| Adversarial Training for Robust Coverage Network under Worst-case Facility Losses | Agents | Changhao Miao +4 | May 26, 2026 | — |
| Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling | Vision & multimodal | Pengzhen Chen +5 | May 26, 2026 | — |
| Near-Optimal Regret in Adversarial Kernel Bandits | Safety & alignment | Yu-Jie Zhang +3 | May 26, 2026 | — |
| Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference | Robotics | Jaewoo Lee +11 | May 26, 2026 | — |
| CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer's Disease Pathologies | Vision & multimodal | Geonwoo Baek +1 | May 26, 2026 | — |
| Foundations of a Time-Consistent Counterfactual Actuarial Runtime for Autonomous AI Agents | Agents | Hao-Hsuan Chen | May 26, 2026 | — |
| Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization | Vision & multimodal | Xiang Fang +2 | May 26, 2026 | — |
| Variational Inference for Evidential Deep Learning | Vision & multimodal | Jiawei Tang +4 | May 26, 2026 | — |
| Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions | Code | Matthew Kutakh | May 26, 2026 | — |
| Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance | Efficiency & systems | Jose Blanchet +2 | May 25, 2026 | — |
| Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models | Code | Inés Gonzalez-Pepe +3 | May 25, 2026 | — |
| Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables | Code | Weizhi Fei +5 | May 25, 2026 | — |
| Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation | Vision & multimodal | David Košťál +1 | May 25, 2026 | — |
| Invariant-Based Weight Sharing for Message Passing | Data & benchmarks | Florian Seiffarth | May 25, 2026 | — |
| Meta-Engineering Harnesses for AI-Native Software Production: A Contract-Driven Adversarial Verification Architecture with Early Deployment Report | Agents | Satadru Sengupta +2 | May 25, 2026 | — |
| Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks | Other | Florent Tariolle +1 | May 25, 2026 | — |
| Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents | Agents | Hao-Hsuan Chen | May 25, 2026 | — |
| DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning | Agents | Guochao Jiang +5 | May 25, 2026 | — |
| Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation | Speech & audio | Chunzheng Zhu +7 | May 25, 2026 | — |
| Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultrasound Plane Quality Control | Speech & audio | Chunzheng Zhu +7 | May 25, 2026 | — |
| Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation | Vision & multimodal | Ruoxi Cheng +8 | May 25, 2026 | — |
| When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers | Robotics | Aditya Sridhar | May 25, 2026 | — |
| Adversarial Water-Filling: Theory, Algorithms and Foundation Model | Code | Xindi Tong +2 | May 24, 2026 | — |
| SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack | Data & benchmarks | Han Liu +7 | May 24, 2026 | — |
| Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting | Theory | Jinjin Chi +8 | May 24, 2026 | — |
| Adversarial Error Correction for Visual Autoregressive Generation | Image & video gen | Ligong Bi +3 | May 24, 2026 | — |
| Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection | Safety & alignment | Lixing Lin +6 | May 24, 2026 | — |
| DUEL: Adversarial Self-Play for Multimodal Reasoning | Image & video gen | Lin Qiu +5 | May 24, 2026 | — |
| Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants | Science & bio | Emanuele Guidotti +1 | May 23, 2026 | — |
| The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty | Efficiency & systems | Volodymyr Ovcharov | May 23, 2026 | — |
| WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains | Science & bio | Bokai Zhu +2 | May 23, 2026 | — |
| Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation | Safety & alignment | Luoyu Chen +7 | May 23, 2026 | — |
| Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems | Efficiency & systems | Imesh Ekanayake +2 | May 23, 2026 | — |
| Phonetic Modeling of Dialectal Variation in Vietnamese Speech | Speech & audio | Quan Ngoc Hoang +4 | May 23, 2026 | — |
| Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content | Robotics | Rohan Pandey +1 | May 23, 2026 | — |
| Private Adaptive Covariance Estimation via Gaussian Graphical Models | Data & benchmarks | Cecilia Ferrando +4 | May 22, 2026 | — |
| DRInQ: Evaluating Conversational Implicature with Controlled Context Variation | Safety & alignment | Hirona Jacqueline Arai +1 | May 22, 2026 | — |
| Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction | Safety & alignment | Siqi Li +11 | May 22, 2026 | — |
| Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment | Vision & multimodal | Haoyuan Wang +4 | May 22, 2026 | — |
| Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series | Vision & multimodal | Yunhua Pei +3 | May 22, 2026 | — |
| Valid and Expressive Copulas for Irregular Multivariate Time Series | Other | Christian Klötergens +3 | May 22, 2026 | — |
| Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection | Speech & audio | Ahmed Sabbah +4 | May 22, 2026 | — |
| Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs | Theory | Lucia Celli | May 22, 2026 | — |
| Articulatory strategy as a source of variation in acoustic vowel dynamics | Speech & audio | Patrycja Strycharczuk +2 | May 22, 2026 | — |
| Sample-wise Targeted Adversarial Attacks on Test-time Adaptation | Robotics | Phuc Duc Nguyen +1 | May 22, 2026 | — |
| Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays | Safety & alignment | Ting Hu +2 | May 22, 2026 | — |
| Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution | Safety & alignment | Hongbo Wang +5 | May 22, 2026 | — |