Ax Alejandro Luque-Cerpa, Mengyuan Wang, Emil Carlsson, Sanjit A. Seshia, Devdatt Dubhashi, Hazem Torfah 4/3/2026

Learning Contextual Runtime Monitors for Safe AI-Based Autonomy

Context-aware runtime monitors for safe AI-based autonomous systems using ensemble ML controllers.

Ax Shihao Shao, Cong Fang, Zhouchen Lin, Dacheng Tao 4/3/2026

Partial Feedback Online Learning

Theoretical framework for online learning with partial feedback and collection version spaces.

Ax Anderson de Andrade, Alon Harell, Ivan V. Baji\'c 4/3/2026

Rate-Distortion Optimization for Transformer Inference

Rate-distortion framework for lossy compression of transformer intermediate representations to reduce inference compute and memory.

Ax Zeyuan He, Yupeng Chen, Lang Lin, Yihan Wang, Shenxu Chang, Eric Sommerlade, Philip Torr, Junchi Yu, Adel Bibi, Jialin Yu 4/3/2026

Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode

Analysis of safety properties in diffusion-based LLMs versus autoregressive LLMs, showing robustness against jailbreak attacks.

Ax Jayadev Billa 4/3/2026

The Geometric Anatomy of Capability Acquisition in Transformers

Study of capability acquisition in transformers tracking geometric changes and linear probes across model scales and algorithmic task difficulty levels.

Ax Aran Nayebi 4/3/2026

What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty

Quantitative selection theorems proving that strong task performance under uncertainty necessitates world models and belief-like memory structures in agents.

Ax Haichen Hu, David Simchi-Levi 4/3/2026

Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors

Efficient evaluation algorithm for excess risk of large-scale empirical risk minimization using black-box access with single dataset.

Ax Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz, Alain Ryser, Irene Cannistraci, Julia E. Vogt 4/3/2026

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion

Machine unlearning approach using key deletion in model architecture for privacy-compliant data removal without requiring full training data access.

Ax Mohammad Al Ridhawi, Mahtab Haj Ali, Hussein Al Osman 4/3/2026

Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control

Adaptive stock price prediction framework using autoencoder-gated dual node transformers with RL control for regime-dependent market behavior.

Ax Ming Shi, Yingbin Liang, Ness B. Shroff, Ananthram Swami 4/3/2026

Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences

Theoretical framework for RLHF with multi-source imperfect preferences, deriving regret bounds when feedback comes from multiple annotators with systematic mismatches.

Ax Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kaichen Yang, Ziang Yan, Jun Xu, Yicheng Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Ruiliang Xu, Shuhao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wen Wu, Fan Wu, Xilin Wei, Qi Wei, Bingli Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjiang Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huanze Tang, Chen Tang, Shixiang Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qisheng Su, Chenlin Su, Demin Song, Jin Shi, Fukai Shang, Yuchen Ren, Pengli Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Biqing Qi, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuoshi Pan, Linke Ouyang, Wenchang Ning, Yichuan Ma, Zerun Ma, Ningsheng Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv, Lindong Lu, Kuikun Liu, Jiangning Liu, Yuhong Liu, Kai Liu, Hongwei Liu, Zhoumianze Liu, Mengjie Liu, Ziyu Liu, Wenran Liu, Yang Liu, Liwei Liu, Kaiwen Liu, Junyao Lin, Junming Lin, Tianyang Lin, Dahua Lin, Jianze Liang, Linyang Li, Peiji Li, Zonglin Li, Zehao Li, Pengze Li, Guoyan Li, Lingkai Kong, Linglin Jing, Zhenjiang Jin, Feifei Jiang, Qian Jiang, Junhao Huang, Zixian Huang, Haian Huang, Zhouqi Hua, Ermo Hua, Han Hu, Linfeng Hou, Yinan He, Conghui He, Tianyao He, Xu Guo, Qipeng Guo, Aijia Guo, Yuzhe Gu, Lixin Gu, Jingyang Gong, Qiming Ge, Jiaye Ge, Songyang Gao, Jianfei Gao, Xinyu Fang, Caihua fan, Yue Fan, Yanhui Duan, Zichen Ding, Shengyuan Ding, Ning Ding, Xuanlang Dai, Erfei Cui, Ganqu Cui, Pei Chu, Tao Chu, Guangran Cheng, Yu Cheng, Kai Chen, Yongkang Chen, Chiyu Chen, Guanzhou Chen, Qiaosheng Chen, Sitao Chen, Xin Chen, Haojiong Chen, Yicheng Chen, Weihan Cao, Yuhang Cao, Qinglong Cao, Lei Bai 4/3/2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Trillion-parameter scientific multimodal foundation model with advanced agent capabilities spanning 100+ scientific domains and general reasoning tasks.

Ax Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli 4/3/2026

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

Method for learning low-dimensional policy manifolds in reinforcement learning through state-occupancy matching to improve sample efficiency.

Ax Tanvir Hossain, Muhammad Ifte Khairul Islam, Lilia Chebbah, Charles Fanning, Esra Akbas 4/3/2026

Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs

Novel GNN architecture using cross-attentive cohesive subgraph embedding to address oversquashing and improve information flow in graph neural networks.

Ax Arsenios Scrivens 4/3/2026

Information-Theoretic Limits of Safety Verification for Self-Improving Systems

Theoretical analysis of safety verification limits for self-improving AI systems, formalizing compatibility between bounded risk and unbounded utility.

Ax Amirreza Alasti, Efe Erdal, Y\"ucel Celik, Theresa Eimer 4/3/2026

Learning to Play Blackjack: A Curriculum Learning Perspective

Uses LLM to dynamically generate curriculum over actions for RL agents, progressively introducing complex actions during training.

Ax Weyl Lu, Chenjie Hao, Yubei Chen 4/3/2026

Deep Networks Favor Simple Data

Studies how deep networks assign higher density to simpler out-of-distribution data than in-distribution test data.

Ax Junxian Wu, Chenghan Fu, Zhanheng Nie, Daoze Zhang, Bowen Wan, Wanxian Guan, Chuan Yu, Jian Xu, Bo Zheng 4/3/2026

MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding

Multimodal representation learning framework for e-commerce product understanding combining reasoning with product attributes.

Ax Marwan Hassani, Tamara Verbeek, Sjoerd van Straten 4/3/2026

Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction

Prompt-based continual learning method for next activity prediction that handles concept drift without catastrophic forgetting.

Ax Zhanzhi Lou, Hui Chen, Yibo Li, Qian Wang, Bryan Hooi 4/3/2026

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

Language agents that learn adaptive policies at test-time through environment interactions, improving performance via iterative refinement.

Ax Zhantao Chen, Dongyi He, Jin Fang, Xi Chen, Yishuo Liu, Xiaozhen Zhong, Xuejun Hu 4/3/2026

Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling

Data-driven framework using skeleton-based biomechanical analysis and motion modeling for personalized dart training.

Ax Xiangpeng Li, Yu-Hsuan Ho, Sam D Brody, Ali Mostafavi 4/3/2026

Property-Level Flood Risk Assessment Using AI-Enabled Street-View Lowest Floor Elevation Extraction and ML Imputation Across Texas

Pipeline using street-view image analysis and ML imputation to extract building elevation data for flood risk assessment in Texas.

Ax Amin Farajzadeh, Animesh Yadav, Halim Yanikomeroglu 4/3/2026

Tackling Non-IIDness in HAPS-Aided Federated Learning

Federated learning approach using HAPS networks with weighted client selection to handle non-IID data distributions.

Ax Kwangho Kim, Jisu Kim, Edward H. Kennedy 4/3/2026

Causal K-Means Clustering

Causal k-means clustering algorithm to identify heterogeneous treatment effects across unknown subgroups.

Ax Changdae Oh, Gyeongdeok Seo, Geunyoung Jung, Zhi-Qi Cheng, Hosik Choi, Jiyoung Jung, Kyungwoo Song 4/3/2026

Robust Adaptation of Foundation Models with Black-Box Visual Prompting

Parameter-efficient adaptation method for foundation models via black-box visual prompting without full parameter access.

Ax Ayoub Belhadji, Daniel Sharp, Youssef Marzouk 4/3/2026

Weighted quantization using MMD: From mean field to mean shift via gradient flows

Framework for approximating probability distributions using weighted particles via maximum mean discrepancy and gradient flows.

Ax Marta Adamska, Daria Smirnova, Hamid Nasiri, Zhengxin Yu, Peter Garraghan 4/3/2026

Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference

Empirical study measuring how prompt and response characteristics impact energy consumption and inference costs of LLM operations.

Ax Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm, Brian Hu Zhang 4/3/2026

A Polynomial-Time Algorithm for Variational Inequalities under the Minty Condition

Develops polynomial-time algorithm for solving Stampacchia variational inequalities under the Minty condition.

Ax Junhui Zhang, Patrick Jaillet 4/3/2026

Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization

Proposes multi-timescale variants of primal-dual hybrid gradient algorithm for distributed optimization problems.

Ax Abdullah All Tanvir, Frank Y. Shih, Xin Zhong 4/3/2026

InvZW: Invariant Feature Learning via Noise-Adversarial Training for Robust Image Zero-Watermarking

Deep learning framework for image zero-watermarking using noise-adversarial training to learn distortion-invariant features.

Ax Kay Giesecke, Enguerrand Horel, Chartsiri Jirachotkulthorn 4/3/2026

AICO: Feature Significance Tests for Supervised Learning

Introduces AICO, a tool for testing feature significance in supervised learning models to improve interpretability and fairness.

Ax Alex Markham, Isaac Hirsch, Jeri A. Chang, Liam Solus, Bryon Aragam 4/3/2026

Intervening to Learn and Compose Causally Disentangled Representations

Presents method to train generative models that learn causally disentangled latent representations using context modules.

Ax David J Poland 4/3/2026

Boosted Enhanced Quantile Regression Neural Networks with Spatiotemporal Permutation Entropy for Complex System Prognostics

Proposes boosted quantile regression neural networks with entropy analysis for predicting patterns in complex dynamical systems.

Ax Eoghan Cunningham, James Cross, Derek Greene 4/3/2026

Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias

Evaluates 5 LLMs on fairness and inclusion bias in summarizing parliamentary proceedings, measuring representation gaps across demographic groups.

Ax Yunbum Kook, Santosh S. Vempala 4/3/2026

Zeroth-order Logconcave Sampling

Theoretical study of zeroth-order query complexity for sampling from logconcave distributions using only function evaluations, no gradient information required.

Ax Dean Brandner, Sebastien Gros, Sergio Lucia 4/3/2026

Computationally efficient Gauss-Newton reinforcement learning for model predictive control

Gauss-Newton reinforcement learning method for model predictive control offering second-order convergence with faster training than first-order RL methods.

Ax Ruiyu Zhang, Lin Nie, Xin Zhao 4/3/2026

HEAS: Hierarchical Evolutionary Agent-Based Simulation Framework for Multi-Objective Policy Search

HEAS framework for agent-based simulation combining hierarchical evolution with metric standardization to improve multi-objective policy search in complex systems.

Ax Aida Kostikova, Ole P\"utz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen 4/3/2026

LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade

Uses LLMs to analyze 150+ years of German parliamentary debates on migration, demonstrating constraint-free large-scale political text analysis without manual annotation.

Ax Anjiang Wei, Tianran Sun, Tarun Suresh, Haoze Wu, Ke Wang, Alex Aiken 4/3/2026

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis

LLM-based framework for loop invariant synthesis to accelerate program verification with sound evaluation methodology.

Ax Daofu Zhang, Mehrdad Pournaderi, Hanne M. Clifford, Yu Xiang, Pramod K. Varshney 4/3/2026

On the Adversarial Robustness of Learning-based Conformal Novelty Detection

Study of adversarial robustness in conformal novelty detection using learning-based frameworks with FDR guarantees.

Ax Etienne Gauthier, Francis Bach, Michael I. Jordan 4/3/2026

Adaptive Coverage Policies in Conformal Prediction

Method for adapting coverage levels in conformal prediction based on individual sample characteristics.

Ax Hao Yan, Heyan Zhang, Yongyi Guo 4/3/2026

Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation

Framework for linear contextual bandits leveraging pretrained models for feature imputation in partially observed contexts.

Ax Murad Dawood, Usama Ahmed Siddiquie, Shahram Khorshidi, Maren Bennewitz 4/3/2026

Constraint-Aware Reinforcement Learning via Adaptive Action Scaling

Safe reinforcement learning approach using adaptive action scaling to reduce constraint violations during training.

Ax Hongyu Zhu, Lin Chen, Xin Jin, Mingsheng Shang 4/3/2026

MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis

Sentiment-guided augmentation technique for multimodal sentiment analysis addressing data scarcity in video, audio, and text.

Ax Dan Jacobellis, Mateen Ulhaq, Fabien Racap\'e, Hyomin Choi, Neeraja J. Yadwadkar 4/3/2026

DeDelayed: Deleting Remote Inference Delay via On-Device Correction

System for reducing remote video inference latency through on-device correction with lightweight models for robotics and edge devices.

Ax Elias Hossain, Mehrdad Shoeibi, Ivan Garibay, Niloofar Yousefi 4/3/2026

BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance

Multi-agent framework using LLMs for interpreting gene clusters from RNA-seq data in antimicrobial resistance research.

Ax Petr Pt\'a\v{c}ek, Paulina Lewandowska, Ryszard Kukulski 4/3/2026

Resource-Efficient Variational Quantum Classifier

Quantum classifier using Hamming distance measurements with classical post-processing for improved noise robustness.

Ax Dachuan Zhao, Weiyue Li, Zhenda Shen, Yushu Qiu, Bowen Xu, Haoyu Chen, Yongchao Chen 4/3/2026

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

Geometric approach to post-hoc debiasing in vision-language models by treating bias as subspace rather than individual coordinates.

Ax Sonia Laguna, Andrea Agostini, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M. Sutter, Julia E. Vogt 4/3/2026

Structure is Supervision: Multiview Masked Autoencoders for Radiology

Self-supervised learning framework using masked autoencoders to learn view-invariant representations from multi-view radiology data.

Ax Yuang Geng, Zhuoyang Zhou, Zhongzheng Zhang, Siyuan Pan, Hoang-Dung Tran, Ivan Ruchkin 4/3/2026

Deterministic World Models for Verification of Closed-loop Vision-based Systems

Deterministic world models for verification of vision-based control systems avoiding stochastic latent variable overapproximation.

Ax David M\"uller, Espen Knoop, Dario Mylonopoulos, Agon Serifi, Michael A. Hopkins, Ruben Grandia, Moritz B\"acher 4/3/2026

Olaf: Bringing an Animated Character to Life in the Physical World

Reinforcement learning approach to control stylized motion of animated character robot using animation references.