Ax Christin Pagels, Simon Hacks, Rob Henk Bemthuis 4/2/2026

Large Language Models for Analyzing Enterprise Architecture Debt in Unstructured Documentation

LLM-based approach to identify enterprise architecture debt indicators from unstructured documentation in organizations.

Ax Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya 4/2/2026

Generalizable Dense Reward for Long-Horizon Robotic Tasks

Framework combining vision language models with RL for dense reward generation in long-horizon robotic tasks to reduce manual reward engineering.

Ax Lei Huang, Chuan Qiu, Kuan-Jui Su, Anqi Liu, Yun Gong, Weiqiang Lin, Lindong Jiang, Chen Zhao, Meng Song, Jeffrey Deng, Qing Tian, Zhe Luo, Ping Gong, Hui Shen, Chaoyang Zhang, Hong-Wen Deng 4/2/2026

GenoBERT: A Language Model for Accurate Genotype Imputation

GenoBERT uses transformers for reference-free genotype imputation without ancestry bias.

Ax Zhenxuan Li, Meng Huang 4/2/2026

Scaled Gradient Descent for Ill-Conditioned Low-Rank Matrix Recovery with Optimal Sampling Complexity

Theoretical analysis of scaled gradient descent for low-rank matrix recovery with optimal sampling complexity.

Ax Pierre Andreoletti (IDP) 4/2/2026

Forecast collapse of transformer-based models under squared loss in financial time series

Analysis of transformer forecast collapse under squared loss for financial time series with weak conditional structure.

Ax Luca Cattelani, Vittorio Fortino 4/2/2026

Genetic algorithms for multi-omic feature selection: a comparative study in cancer survival analysis

Genetic algorithms for multi-objective feature selection in cancer biomarker discovery from omics data.

Ax Eugene Lee, Ting-Yu Chang, Jui-Huang Tsai, Jiajie Diao, Chen-Yi Lee 4/2/2026

Hierarchical Pre-Training of Vision Encoders with Large Language Models

HIVE framework for hierarchical pre-training of vision encoders integrated with large language models for vision-language alignment.

Ax Sameer Shaik, Zhen Huang, Daniela Stan Raicu, Jacob Furst 4/2/2026

Efficient Software Vulnerability Detection Using Transformer-based Models

Transformer-based models for detecting software vulnerabilities in C/C++ using program slices.

Ax Yitao Bai, Thinh T. Doan, Justin Romberg 4/2/2026

Finite-Time Analysis of Projected Two-Time-Scale Stochastic Approximation

Finite-time convergence analysis of two-time-scale stochastic approximation algorithms.

Ax Ali Sayedsalehi, Peter C. Rigby, Gregory Mierzwinski 4/2/2026

Risk-Aware Batch Testing for Performance Regression Detection

Performance regression detection for CI systems using risk-aware batch testing and predictive models.

Ax Simone Betteti, Luca Laurenti 4/2/2026

Hybrid Energy-Based Models for Physical AI: Provably Stable Identification of Port-Hamiltonian Dynamics

Energy-based models for stable system identification in physical AI using port-Hamiltonian dynamics.

Ax Yanliang Huang, Peng Xie, Wenyuan Wu, Zhuoqi Zeng, Amr Alanwar 4/2/2026

Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees

Data-driven reachability analysis for dynamical systems using diffusion models with PAC theoretical guarantees.

Ax Sahil Kumar, Namrataben Patel, Honggang Wang, Youshan Zhang 4/2/2026

MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control

MambaVoiceCloning uses state-space models and diffusion for efficient text-to-speech synthesis without attention layers.

Ax Fan Wu, Matthias P. N\"agele, Daryush D. Mehta, Elgar Fleisch, Frank Ruschitzka, Andreas J. Flammer, Filipe Barata 4/2/2026

Vocal Prognostic Digital Biomarkers in Monitoring Chronic Heart Failure: A Longitudinal Observational Study

Medical study using voice features to predict health deterioration in chronic heart failure patients via ML models.

Ax Marcel Tom\`as Bernal, Neil Rohit Mallinar, Mikhail Belkin 4/2/2026

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

Studies grokking in feature learning kernels via Recursive Feature Machine, showing data symmetry breaking is necessary for generalization.

Ax Liyao Lyu, Xinyue Yu, Hayden Schaeffer 4/2/2026

MVNN: A Measure-Valued Neural Network for Learning McKean-Vlasov Dynamics from Particle Data

Measure-valued neural network learning McKean-Vlasov dynamics from particle trajectories using cylindrical feature embeddings.

Ax Borislav Mavrin 4/2/2026

In harmony with gpt-oss

Reverse-engineers gpt-oss-20b tool definitions from in-distribution calls and builds native harmony agent harness with open-source implementation.

Ax Wei Sun 4/2/2026

Decision-Centric Design for LLM Systems

Proposes decision-centric framework separating control decisions (answer, retrieve, tool use) from LLM generation in agent architectures.

Ax Weizhuo Wang, Yanjie Ze, C. Karen Liu, Monroe Kennedy III 4/2/2026

Learning Humanoid Navigation from Human Data

EgoNav: Humanoid robot navigation system trained on 5 hours of human walking data using diffusion models and frozen DINOv3 backbone.

Ax Xinyu Sun, Wanwei Liu, Haoang Chi, Tingyu Chen, Xiaoguang Mao, Shangwen Wang, Lei Bu, Jingyi Wang, Yang Tan, Zhenyi Qi 4/2/2026

Shapley-Guided Neural Repair Approach via Derivative-Free Optimization

Shapley-guided approach using derivative-free optimization to repair DNNs affected by backdoors, adversarial attacks, and unfairness.

Ax Han Huang, Pakawut Jiradilok, Elchanan Mossel 4/2/2026

Denoising distances beyond the volumetric barrier

Theoretical work on reconstructing latent manifold geometry from random geometric graphs beyond volumetric constraints.

Ax Wonseok Yang, Thinh T. Doan 4/2/2026

Internal State-Based Policy Gradient Methods for Partially Observable Markov Potential Games

Studies policy gradient methods for multi-agent reinforcement learning in partially observable Markov potential games.

Ax Michael Maynord, Minghui Liu, Cornelia Ferm\"uller, Seongjin Choi, Yuxin Zeng, Shishir Dahal, Daniel M. Harrison 4/2/2026

Automated Detection of Multiple Sclerosis Lesions on 7-tesla MRI Using U-net and Transformer-based Segmentation

Compares U-net and Transformer-based segmentation for detecting multiple sclerosis lesions on 7-tesla MRI.

Ax Yabin Zhang, Chong Wang, Yunhe Gao, Jiaming Liu, Maya Varma, Justin Xu, Sophie Ostmeier, Jin Long, Sergios Gatidis, Seena Dehkharghani, Arne Michalson, Eun Kyoung Hong, Christian Bluethgen, Haiwei Henry Guo, Alexander Victor Ortiz, Stephan Altmayer, Sandhya Bodapati, Joseph David Janizek, Ken Chang, Jean-Benoit Delbrouck, Akshay S. Chaudhari, Curtis P. Langlotz 4/2/2026

A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation

CheXOne: Vision-language foundation model for chest X-ray interpretation with explicit reasoning about visual evidence.

Ax Zixiang Peng, Yongxiu Xu, Qinyi Zhang, Jiexun Shen, Yifan Zhang, Hongbo Xu, Yubin Wang, Gaopeng Gou 4/2/2026

Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models

Introduces Uni-SafeBench, a safety benchmark for unified multimodal large models testing both understanding and generation capabilities.

Ax Simone Garatti, Lucrezia Manieri, Alessandro Falsone, Algo Car\`e, Marco C. Campi, Maria Prandini 4/2/2026

Scenario theory for multi-criteria data-driven decision making

Extends scenario approach theory for multi-criteria data-driven decision-making with probabilistic robustness guarantees.

Ax Yichen Xie, Yixiao Wang, Shuqi Zhao, Cheng-En Wu, Masayoshi Tomizuka, Jianwen Xie, Hao-Shu Fang 4/2/2026

Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning

Framework for robot imitation learning using multi-camera view scaling to improve generalization from limited expert demonstrations.

Ax Stefano Cortinovis, Laurence Aitchison, Stefanos Eleftheriadis, Mark van der Wilk 4/2/2026

Inverse-Free Sparse Variational Gaussian Processes

Proposes inverse-free sparse variational Gaussian processes using only matrix multiplications for low-precision parallel hardware.

Ax Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao, Sachin Kumar, Emmy Liu, Steven Y. Feng 4/2/2026

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining

Studies trade-off between pretraining corpus size and retrieval-augmented generation for language models under fixed data budgets.

Ax Rajkiran Panuganti 4/2/2026

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection

CircuitProbe predicts reasoning circuits in Transformers from activation statistics in under 5 minutes, achieving 3-4 orders of magnitude speedup over brute-force methods.

Ax Merveilles Agbeti-messan, Thierry Paquet, Cl\'ement Chatelain, Pierrick Tranouez, St\'ephane Nicolas 4/2/2026

A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR

Benchmarks State-Space Models (Mamba) against Transformers and BiLSTM for historical newspaper OCR, addressing quadratic complexity limitations.

Ax Ricardo Hidalgo-Arag\'on, Jes\'us M. Gonz\'alez-Barahona, Gregorio Robles 4/2/2026

A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch

CEFR-aligned framework with fuzzy C-means for automated assessment of programming skills in Scratch.

Ax Zehao Jin, Yanan Sui 4/2/2026

Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention

Stochastic Attention inspired by connectome topology provides linear-time expressive attention mechanism.

Ax Paolo Speziali, Arno De Greef, Mehrdad Asadi, Willem R\"opke, Ann Now\'e, Diederik M. Roijers 4/2/2026

Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning

PG-IPRO algorithm for interactive multi-objective route planning with accessibility preferences.

Ax Om Khangaonkar, Hadi J. Rad, Hamed Pirsiavash 4/2/2026

Multimodal Language Models Cannot Spot Spatial Inconsistencies

Study shows multimodal LLMs fail at detecting 3D spatial inconsistencies across multiple views.

Ax Oscar Clivio, Alexander D'Amour, Alexander Franks, David Bruns-Smith, Chris Holmes, Avi Feller 4/2/2026

Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap

Deconfounding scores for causal effect estimation preserve treatment-control distinctions in high dimensions.

Ax Deepak Nathani, Cheng Zhang, Chang Huan, Jiaming Shan, Yinfei Yang, Alkesh Patel, Zhe Gan, William Yang Wang, Michael Saxon, Xin Eric Wang 4/2/2026

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants

PARE framework simulates realistic user interactions for evaluating proactive AI agents and assistants.

Ax Guanlin He, Yingtai Xiao, Jiamu Bai, Xin Gu, Zeyu Ding, Wenpeng Yin, Daniel Kifer 4/2/2026

Accurate and Scalable Matrix Mechanisms via Divide and Conquer

Divide-and-conquer approach for scalable matrix mechanisms in differential privacy and synthetic data.

Ax Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain, K. M. Azharul Hasan 4/2/2026

KUET at StanceNakba Shared Task: StanceMoE: Mixture-of-Experts Architecture for Stance Detection

StanceMoE uses mixture-of-experts for actor-level stance detection in geopolitical texts.

Ax Razvan Mihai Popescu, David Gros, Andrei Botocan, Rahul Pandita, Prem Devanbu, Maliheh Izadi 4/2/2026

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Dataset and analysis of autonomous coding agent contributions to real-world GitHub projects over time.

Ax Gilhan Kim, Daniel K. Park 4/2/2026

Multi-Mode Quantum Annealing for Variational Autoencoders with General Boltzmann Priors

Quantum annealing for VAEs with general Boltzmann priors enables structured latent variable interactions.

Ax Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang, Yiduo Guo, Ziniu Li, Chenxin Li, Jingyuan Hu, Shunian Chen, Tongxu Luo, Jiaxi Bi, Zeyu Qin, Shaobo Wang, Xin Lai, Pengyuan Lyu, Junyi Li, Can Xu, Chengquan Zhang, Han Hu, Ming Yan, Benyou Wang 4/2/2026

Do Phone-Use Agents Respect Your Privacy?

MyPhoneBench evaluates privacy compliance of mobile phone-use agents completing benign tasks.

Ax Jalo Nousiainen, Iremsu Taskin, Markus Kasper, Gilles Orban De Xivry, Olivier Absil 4/2/2026

Focal plane wavefront control with model-based reinforcement learning

Model-based RL controls focal plane wavefront for exoplanet imaging on extremely large telescopes.

Ax Yiheng Wang, Lichen Zhu, Yueqian Lin, Yudong Liu, Jingyang Zhang, Hai "Helen" Li, Yiran Chen 4/2/2026

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding

Query-conditioned evidential keyframe sampling for efficient multimodal LLM-based long-form video understanding.

Ax Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Di Wen, Danda Pani Paudel, Luc Van Gool, Kailun Yang 4/2/2026

ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction

ProOOD method for 3D semantic occupancy prediction handles out-of-distribution inputs and long-tailed class bias.

Ax Jonas Schaible, Asena Karolin \"Ozdemir, Charlotte Debus, Sven Burger, Achim Streit, Christiane Becker, Klaus J\"ager, Markus G\"otz 4/2/2026

Inverse Design of Optical Multilayer Thin Films using Robust Masked Diffusion Models

OptoLlama uses masked diffusion models for inverse design of optical multilayer thin films.

Ax Reyhaneh Ahani Manghotay (Simon Fraser University, Burnaby, Canada), Jie Liang (Eastern Institute of Technology, Ningbo, China) 4/2/2026

Lightweight Prompt-Guided CLIP Adaptation for Monocular Depth Estimation

MoA-DepthCLIP adapts CLIP vision-language model for monocular depth estimation with parameter-efficient adapters.

Ax Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao, Kenta Watanabe, Toshihiko Yamasaki, Kiyoharu Aizawa 4/2/2026

Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

PaperRecon framework evaluates quality and hallucination risks in papers generated by AI coding agents.

Ax Shaifalee Saxena, Rafael Fierro, Alexander Scheinker 4/2/2026

Deep Reinforcement Learning for Robotic Manipulation under Distribution Shift with Bounded Extremum Seeking

RL policy adaptation for robotic manipulation under distribution shift using bounded extremum seeking.

Ax Aaron Rose, Carissa Cullen, Brandon Gary Kaplowitz, Christian Schroeder de Witt 4/2/2026

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

NARCBench for detecting multi-agent collusion using multi-agent interpretability on LLM agent activations.