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.

Ax Jack Young 4/2/2026

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

S0 tuning zero-overhead adaptation of hybrid recurrent-attention models outperforming LoRA on code generation.

Ax Abdullah Tokmak, Toni Karvonen, Thomas B. Sch\"on, Dominik Baumann 4/2/2026

Safe learning-based control via function-based uncertainty quantification

Function-based uncertainty quantification for safe learning-based control in safety-critical systems.

Ax Fangjun Hu, Christian Kokail, Milan Kornja\v{c}a, Pedro L. S. Lopes, Weiyuan Gong, Sheng-Tao Wang, Xun Gao, Stefan Ostermann 4/2/2026

Learning and Generating Mixed States Prepared by Shallow Channel Circuits

Learning to generate mixed quantum states prepared by shallow channel circuits in trivial phases.

Ax Yiheng Su, Matthew Lease 4/2/2026

LLM REgression with a Latent Iterative State Head

RELISH lightweight architecture for text regression with LLMs using iterative latent state refinement.

Ax Shichang Zhang (Celine), Atefeh Sohrabizadeh (Celine), Cheng Wan (Celine), Zijie Huang (Celine), Ziniu Hu (Celine), Yewen Wang (Celine), Yingyan (Celine), Lin, Jason Cong, Yizhou Sun 4/2/2026

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware

Survey on Graph Neural Network acceleration techniques across algorithms, systems, and customized hardware.

Ax Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, Prateek Mittal 4/2/2026

Certifiably Robust RAG against Retrieval Corruption

RobustRAG defense framework with certifiable robustness against retrieval corruption attacks on RAG systems.

Ax Jungeum Kim, Xiao Wang 4/2/2026

Inductive Global and Local Manifold Approximation and Projection

Inductive manifold learning approach for nonlinear dimensional reduction with local and global structure.

Ax Kulunu Dharmakeerthi, YoonHaeng Hur, Tengyuan Liang 4/2/2026

Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction

Domain adaptation with distribution shifts and unobserved confounding using linear structural causal models.

Ax Tiago F. Tavares, Fabio Ayres, Paris Smaragdis 4/2/2026

Diagnosing Neural Convergence with Topological Alignment Spectra

Topological Alignment Spectra method for analyzing multi-scale structural relationships in neural network representations.

Ax Sergio Calvo-Ordo\~nez, Jonathan Plenk, Richard Bergna, Alvaro Cartea, Jose Miguel Hernandez-Lobato, Konstantina Palla, Kamil Ciosek 4/2/2026

A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks

Gaussian Process interpretation of wide neural networks with observation noise and arbitrary prior means.

Ax Ethan Harvey, Mikhail Petrov, Michael C. Hughes 4/2/2026

Learning Hyperparameters via a Data-Emphasized Variational Objective

Gradient-based hyperparameter learning via evidence lower bound objective from Bayesian variational methods.

Ax Yali Wei, Alan J. X. Guo, Zihui Yan, Yufan Dai, Wenjia Fan 4/2/2026

VT-Former: Efffcient Transformer-based Decoder for Varshamov-Tenengolts Codes

Transformer-based decoder for Varshamov-Tenengolts codes correcting insertion, deletion, and substitution errors.

Ax Fateme Jamshidi, Mohammad Shahverdikondori, Negar Kiyavash 4/2/2026

Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference

Multi-armed bandit algorithm using local graph structure to minimize regret under network interference.

Ax Leo Henry, Thomas Neele, Mohammad Reza Mousavi, Matteo Sammartino 4/2/2026

A Detailed Account of Compositional Automata Learning through Alphabet Refinement

Compositional automata learning technique for inferring models of concurrent systems through alphabet refinement.

Ax Stepan Tretiakov, Xingjian Li, Krishna Kumar 4/2/2026

SetONet: A Set-Based Operator Network for Solving PDEs with Variable-Input Sampling

SetONet neural operator for solving PDEs with variable sensor layouts by treating inputs as unordered sets.

Ax Carlos Rodriguez-Pardo, Leonardo Chiani, Emanuele Borgonovo, Massimo Tavoni 4/2/2026

Neural Conditional Transport Maps

Neural framework for learning conditional optimal transport maps using hypernetworks to generate adaptive transport parameters.

Ax Leon Eshuijs, Archie Chaudhury, Alan McBeth, Ethan Nguyen 4/2/2026

But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors

JUSSA framework uses steering vectors to improve LLM-as-a-judge reliability, detecting and mitigating sycophancy through honesty-promoting alternatives.

Ax Rafael Sojo, Javier D\'iaz-Rozo, Concha Bielza, Pedro Larra\~naga 4/2/2026

Binned semiparametric Bayesian networks for efficient kernel density estimation

Binned semiparametric Bayesian networks for efficient kernel density estimation using data binning to reduce computational cost.

Ax Hanlin Dong, Arian Prabowo, Hao Xue, Ao Shuang, Tianyi Zhou, Flora D. Salim 4/2/2026

Double-Diffusion: ODE-Prior Accelerated Diffusion Models for Spatio-Temporal Graph Forecasting

Double-Diffusion integrates ODE-prior with denoising diffusion models for spatio-temporal graph forecasting, balancing deterministic and stochastic components.

Ax Zhenpeng Su, Leiyu Pan, Xue Bai, Dening Liu, Guanting Dong, Jiaming Huang, Minxuan Lv, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou 4/2/2026

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

Klear-Reasoner model with long reasoning capabilities using gradient-preserving clipping policy optimization, with detailed training disclosures.

Ax Muntasir Hoq, Griffin Pitts, Tirth Bhatt, Aum Pandya, Andrew Lan, Peter Brusilovsky, Bita Akram 4/2/2026

Pattern-based Knowledge Component Extraction from Student Code Using Representation Learning

Knowledge component discovery in programming using representation learning on student code for personalized instruction systems.

Ax Mohammad Taha Shah, Sabrina Khurshid, Gourab Ghatak 4/2/2026

Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling

Thompson sampling analysis for Sharpe ratio optimization in multi-armed bandit setting, addressing fractional objective with dependent mean-variance.