Ax Savan Doshi 3/2/2026

Beyond Accuracy: Risk-Sensitive Evaluation of Hallucinated Medical Advice

Risk-sensitive evaluation framework for LLM hallucinations in medical advice, assessing clinical harm severity beyond factual correctness.

Ax Iv\'an Arcuschin, David Chanin, Adri\`a Garriga-Alonso, Oana-Maria Camburu 3/2/2026

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

Automated black-box pipeline detecting unverbalized biases in LLM chain-of-thought reasoning without predefined categories using task-specific evaluation.

Ax Zhen Bi, Xueshu Chen, Luoyang Sun, Yuhang Yao, Qing Shen, Jungang Lou, Cheng Deng 3/2/2026

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis

RooflineBench: Roofline model-based benchmarking framework for characterizing performance of Small Language Models on edge hardware.

Ax Pengfei Zhang, Tianxin Xie, Minghao Yang, Li Liu 3/2/2026

Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis

Agentic system for respiratory disease diagnosis using multimodal sound generation and active adversarial curriculum learning.

Ax Daniel Romero-Alvarado, Fernando Mart\'inez-Plumed, Lorenzo Pacchiardi, Hugo Save, Siddhesh Milind Pawar, Behzad Mehrbakhsh, Pablo Antonio Moreno Casares, Ben Slater, Paolo Bova, Peter Romero, Zachary R. Tyler, Jonathan Prunty, Luning Sun, Jose Hernandez-Orallo 3/2/2026

Capabilities Ain't All You Need: Measuring Propensities in AI

Framework extending Item Response Theory to measure AI model propensities and behavioral tendencies beyond capability metrics.

Ax Rui Liu, Steven Jige Quan, Zhong-Ren Peng, Zijun Yao, Han Wang, Zhengzhang Chen, Kunpeng Liu, Yanjie Fu, Dongjie Wang 3/2/2026

City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

Agentic system for hierarchical urban geospatial modification using multimodal models to handle dependency-aware city planning changes.

Ax Yijiashun Qi, Hanzhe Guo, Yijiazhen Qi 3/2/2026

Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks

Heterogeneous graph transformer framework for predicting high-potential small-medium enterprises using public business data.

Ax Junchen Liu, Sven Elflein, Or Litany, Zan Gojcic, Ruilong Li 3/2/2026

Test-Time Training with KV Binding Is Secretly Linear Attention

Analysis showing test-time training with KV binding can be expressed as learned linear attention mechanism.

Ax Alina Devkota, Jacob Thrasher, Donald Adjeroh, Binod Bhattarai, Prashnna K. Gyawali 3/2/2026

FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning

Federated learning aggregation method using gradient-based weighting to address client drift and data heterogeneity.

Ax Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti 3/2/2026

Provably Safe Generative Sampling with Constricting Barrier Functions

Safety filtering framework for flow-based generative models providing formal guarantees that generated samples satisfy hard constraints.

Ax Chengrui Qu, Yizhou Zhang, Nicolas Lanzetti, Eric Mazumdar 3/2/2026

Training Generalizable Collaborative Agents via Strategic Risk Aversion

Training approach for collaborative AI agents using strategic risk aversion to improve generalization when paired with new partners.

Ax Minghan Yang, Lan Yang, Ke Li, Honggang Zhang, Kaiyue Pang, Yizhe Song 3/2/2026

SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance

Method for reconstructing video content from brain fMRI activity using hierarchical semantic guidance.

Ax Yicheng Bao, Xuhong Wang, Qiaosheng Zhang, Chaochao Lu, Xia Hu, Xin Tan 3/2/2026

To Deceive is to Teach? Forging Perceptual Robustness via Adversarial Reinforcement Learning

Adversarial dataset and training method to improve multimodal LLM robustness when handling visually complex scenes.

Ax Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala, Idan Habler, Ammar Al-Kahfah, Ken Huang, Blake Gatto 3/2/2026

Manifold of Failure: Behavioral Attraction Basins in Language Models

Framework for systematically mapping unsafe regions in LLMs using MAP-Elites quality diversity approach to characterize failure modes.

Ax Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu 3/2/2026

veScale-FSDP: Flexible and High-Performance FSDP at Scale

Improved FSDP implementation supporting structure-aware training and non-element-wise optimizers for large-scale model training.

Ax Bangrui Xu, Qihang Yao, Zirui Tang, Xuanhe Zhou, Yeye He, Shihan Yu, Qianqian Xu, Bin Wang, Guoliang Li, Conghui He, Fan Wu 3/2/2026

MoDora: Tree-Based Semi-Structured Document Analysis System

Document analysis system for semi-structured documents with tables, charts, and hierarchical content for question-answering tasks.

Ax Pengxiang Li, Dilxat Muhtar, Tianlong Chen, Lu Yin, Shiwei Liu 3/2/2026

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Analysis of why diffusion language models converge to autoregressive decoding instead of truly parallel generation despite theoretical advantages.

Ax Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, Daniel M. Roy, Gintare Karolina Dziugaite 3/2/2026

Detoxifying LLMs via Representation Erasure-Based Preference Optimization

Defense method for LLMs against toxic outputs using representation erasure-based preference optimization, more robust than DPO/NPO approaches.

Ax Zezheng Wu, Rui Wang, Xinghe Cheng, Yang Shao, Qing Yang, Jiapu Wang, Jingwei Zhang 3/2/2026

U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation

Machine unlearning technique for generative recommendation systems using LLMs to remove sensitive user attributes from model parameters.

Ax Michael Poppel, Jonas Stein, Sebastian W\"olckert, Markus Baumann, Claudia Linnhoff-Popien 3/2/2026

Long Range Frequency Tuning for QML

Quantum machine learning models using angle encoding with analysis of circuit depth scaling for fixed and trainable-frequency approaches.

Ax Hanning Guo, Farah Abdellatif, Hanwen Bi, Andrei Galbenus, Jon. N. Shah, Abigail Morrison, J\"urgen Dammers 3/2/2026

Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG

Brain-OF is first omnifunctional foundation model jointly pretrained on fMRI, EEG, and MEG brain imaging data.

Ax Shu Liu, Shubham Agarwal, Monishwaran Maheswaran, Mert Cemri, Zhifei Li, Qiuyang Mang, Ashwin Naren, Ethan Boneh, Audrey Cheng, Melissa Z. Pan, Alexander Du, Kurt Keutzer, Alexandros G. Dimakis, Koushik Sen, Matei Zaharia, Ion Stoica 3/2/2026

EvoX: Meta-Evolution for Automated Discovery

EvoX framework combines LLM-driven optimization with evolutionary search for automated discovery of programs, prompts, and algorithms.

Ax Alejandro Rodriguez Dominguez 3/2/2026

Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning

Information-theoretic analysis of human supervision as bottleneck explaining persistent LLM errors from annotation noise and subjectivity.

Ax Yangyi Li, Mengdi Huai 3/2/2026

Uncertainty-aware Language Guidance for Concept Bottleneck Models

Framework using LLM guidance to annotate concepts for interpretable Concept Bottleneck Models with uncertainty awareness.

Ax Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma 3/2/2026

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

FedDAG improves federated learning under data heterogeneity by combining data and gradient similarity for client clustering.

Ax Yicen Li, Jose Antonio Lara Benitez, Ruiyang Hong, Anastasis Kratsios, Paul David McNicholas, Maarten Valentijn de Hoop 3/2/2026

Neural Operators Can Discover Functional Clusters

Theoretical work proving neural operators can discover functional clusters in infinite-dimensional spaces.

Ax Martin \v{C}ern\'y, David Sychrovsk\'y, Filip \'Uradn\'ik, Jakub \v{C}ern\'y 3/2/2026

Active Value Querying to Minimize Additive Error in Subadditive Set Function Learning

Active learning approach for querying values of subadditive set functions with applications to combinatorial optimization.

Ax Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent, Aman Chadha, Tanya Roosta, Ali Jannesari 3/2/2026

Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents

Rudder uses LLM agents to steer prefetching optimization in distributed GNN training for adaptive performance.

Ax Adhyyan Narang, Sarah Dean, Lillian J Ratliff, Maryam Fazel 3/2/2026

Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing

Analysis of learning dynamics when multiple platforms compete for users, showing convergence to poor models under certain conditions.

Ax Asiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M. Steinberg, Cheng Soon Ong 3/2/2026

Flowette: Flow Matching with Graphette Priors for Graph Generation

Flowette uses flow matching with graph neural networks to generate graphs with recurring subgraph motifs.

Ax Xiang Ao 3/2/2026

SDMixer: Sparse Dual-Mixer for Time Series Forecasting

SDMixer proposes sparse dual-stream architecture for multivariate time series forecasting using frequency and temporal analysis.

Ax Dang Sy Duy, Nguyen Duy Chien, Kapil Dev, Jeff Nijsse 3/2/2026

Normalisation and Initialisation Strategies for Graph Neural Networks in Blockchain Anomaly Detection

Systematic ablation study of initialization and normalization strategies for GNNs in blockchain fraud detection.

Ax Kejing Yin, Haizhou Xu, Wenfang Yao, Chen Liu, Zijie Chen, Yui Haang Cheung, William K. Cheung, Jing Qin 3/2/2026

When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion

Benchmark evaluating multimodal fusion of EHR and chest X-rays for clinical decision support under missingness and fairness constraints.

Ax Zhongyi Pei, Zhiyao Cen, Yipeng Huang, Chen Wang, Lin Liu, Philip Yu, Mingsheng Long 3/2/2026

BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization

BTTackler diagnoses training problems in deep learning to guide efficient hyperparameter optimization beyond accuracy-based methods.

Ax Yubo Zhou, Luo Luo, Guang Dai, Haishan Ye 3/2/2026

On the Convergence of Single-Loop Stochastic Bilevel Optimization with Approximate Implicit Differentiation

Theoretical analysis of single-loop stochastic bilevel optimization convergence for meta-learning and hyperparameter optimization.

Ax Zhihao Ding, Jinming Li, Ze Lu, Jieming Shi 3/2/2026

FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation

FlexGuard proposes continuous risk scoring for LLM content moderation that adapts to varying strictness levels across platforms and time.

Ax Haoran Zhang, Dongjun Kim, Seohyeon Cha, Haris Vikalo 3/2/2026

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA

FedRot-LoRA addresses rotational misalignment in federated LoRA fine-tuning of LLMs, improving communication-efficient training on decentralized data.

Ax Kohei Obata, Zheng Chen, Yasuko Matsubara, Lingwei Zhu, Yasushi Sakurai 3/2/2026

Selective Denoising Diffusion Model for Time Series Anomaly Detection

Diffusion-based method for time series anomaly detection using selective denoising instead of conditional reconstruction strategies.

Ax Kohei Obata, Taichi Murayama, Zheng Chen, Yasuko Matsubara, Yasushi Sakurai 3/2/2026

Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning

MoST contrastive learning method for disentangled mode-specific representations in multi-mode tensor time series.

Ax Yongzhong Xu 3/2/2026

Optimizer-Induced Low-Dimensional Drift and Transverse Dynamics in Transformer Training

Geometric analysis of transformer training trajectories revealing low-dimensional drift direction and transverse oscillatory dynamics.

Ax Hanping Zhang, Yuhong Guo 3/2/2026

Bridging Dynamics Gaps via Diffusion Schr\"odinger Bridge for Cross-Domain Reinforcement Learning

BDGxRL uses Diffusion Schrödinger Bridge to address dynamics gaps in cross-domain reinforcement learning without target reward supervision.

Ax Yuyu Geng, Lei Sun, Yao Gao, Xinxin Hu, Zhonghua Yi, Xiaolong Qian, Weijian Hu, Jian Bai, Kaiwei Wang 3/2/2026

OPTIAGENT: A Physics-Driven Agentic Framework for Automated Optical Design

OPTIAGENT uses LLM-based agentic framework with physics-driven optimization for automated optical design and lens system configuration.

Ax Chenxing Lin, Xinhui Gao, Haipeng Zhang, Xinran Li, Haitao Wang, Songzhu Mei, Chenglu Wen, Weiquan Liu, Siqi Shen, Cheng Wang 3/2/2026

MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning

MAGE multi-scale autoregressive generation framework for offline RL addressing long-horizon tasks with sparse rewards via hierarchical decomposition.

Ax Zhiwei Han, Stefan Matthes, Hao Shen 3/2/2026

Provable Subspace Identification of Nonlinear Multi-view CCA

Provable identifiability framework for nonlinear multi-view canonical correlation analysis via subspace identification.

Ax Aleksandr Ananikian (Saint-Petersburg University), Daniil Drozdov (Saint-Petersburg University), Konstantin Yakovlev (Saint-Petersburg University) 3/2/2026

UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding

Learning-based pathfinding using neural networks to approximate informed heuristics for grid-based search across different map topologies.

Ax Tiantong Wang, Xinyu Yan, Tiantong Wu, Yurong Hao, Yong Jiang, Fei Huang, Wei Yang Bryan Lim 3/2/2026

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

MPU framework for privacy-preserving knowledge unlearning in LLMs without sharing server parameters or client forget sets.

Ax Andreas Kernbach, Amr Elsheikh, Nicolas Grupp, Ren\'e Nagel, Marco F. Huber 3/2/2026

Actor-Critic Pretraining for Proximal Policy Optimization

Actor-critic pretraining approach for PPO that leverages expert data to reduce environment interactions required for RL training.

Ax Xiang Li, Nan Jiang, Yuheng Zhang 3/2/2026

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parameteric Policies

Theoretical investigation of offline reinforcement learning with general function approximation and parametric policies beyond state-wise methods.

Ax George Papadopoulos, George A. Vouros 3/2/2026

Learning to maintain safety through expert demonstrations in settings with unknown constraints: A Q-learning perspective

Q-learning approach for learning safe policies from expert demonstrations with unknown constraints in constrained MDPs.

Ax Junkang Liu, Fanhua Shang, Yuxuan Tian, Hongying Liu, Yuanyuan Liu 3/2/2026

FedNSAM:Consistency of Local and Global Flatness for Federated Learning

FedNSAM addresses sharpness-aware minimization in federated learning under high data heterogeneity, ensuring both local and global model flatness.