Ax Chi-Shian Dai, Jun Shao 4/7/2026

Fused Multinomial Logistic Regression Utilizing Summary-Level External Machine-learning Information

Fused multinomial logistic regression leveraging summary-level external machine-learning predictions for data integration.

Ax Fei Wang, Yutong Zhang, Xiong Wang 4/7/2026

Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso

Cross-Modal Graphical Lasso for learning interpretable multimodal representations by disentangling shared and specific topologies.

Ax Pride Kavumba, Koki Wataoka, Huy H. Nguyen, Jiaxuan Li, Masaya Ohagi 4/7/2026

Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming

Value-based safety forecasting for streaming LLM outputs, improving response moderation on partial generations.

Ax Seok-Jin Kim 4/7/2026

Nearly Optimal Best Arm Identification for Semiparametric Bandits

Fixed-confidence best arm identification in semiparametric bandits with instance-optimal sample complexity bounds.

Ax Kay Gijzen (Leiden University), Gertjan J. Burghouts (TNO), Dani\"el M. Pelt (Leiden University) 4/7/2026

OASIC: Occlusion-Agnostic and Severity-Informed Classification

Computer vision method addressing object occlusion through pattern masking and severity-informed classification.

Ax Sailesh kiran kurra, Shiek Ruksana, Vishal Borusu 4/7/2026

Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models

Causal graph-attention approach to detect and mitigate hallucinations in LLMs for improved factual reliability.

Ax Houzhe Wang, Xiaojie Zhu, Chi Chen 4/7/2026

Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement

Jellyfish: Zero-shot federated unlearning scheme using knowledge disentanglement for privacy-preserving federated learning.

Ax Nalin Dhiman 4/7/2026

Topological Sensitivity in Connectome-Constrained Neural Networks

Study on connectome-constrained neural networks and biological graph topology effects on learning efficiency.

Ax Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong 4/7/2026

TORA: Topological Representation Alignment for 3D Shape Assembly

TORA: Topology-first framework for 3D shape assembly using flow-matching and pretrained 3D encoders.

Ax Fatiha Hamdi, Abdelhafid Zeroual, Fouzi Harrou 4/7/2026

Extended Hybrid Timed Petri Nets with Semi-Supervised Anomaly Detection for Switched Systems, Modelling and Fault Detection

Fault detection framework for hybrid dynamical systems combining Petri nets with semi-supervised anomaly detection.

Ax Hang Xu, Ling Yue, Chaoqian Ouyang, Yuchen Liu, Libin Zheng, Shaowu Pan, Shimin Di, Min-Ling Zhang 4/7/2026

FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification

FactReview: LLM-based peer review system that grounds claims in evidence from papers, related work, and code to improve ML paper reviewing.

Ax Shkelqim Sherifi 4/7/2026

Intelligent Traffic Monitoring with YOLOv11: A Case Study in Real-Time Vehicle Detection

Real-time traffic monitoring system using YOLOv11 object detection and multi-object tracking in PyTorch/OpenCV.

Ax Yuanhao Liu, Zihan Zhou, Kaiying Wu, Shuo Liu, Yiyang Huang, Jiajun Guo, Aimin Zhou, Hong Qian 4/7/2026

Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling

Fine-tuned language models enhance embeddings for cognitive diagnosis in online education systems by incorporating semantic representations.

Ax Arunkumar Rathinam, Jules Lecomte, Jost Reelsen, Gregor Lenz, Axel von Arnim, Djamila Aouada 4/7/2026

Efficient Onboard Spacecraft Pose Estimation with Event Cameras and Neuromorphic Hardware

Event camera and neuromorphic hardware approach for efficient spacecraft pose estimation during autonomous rendezvous operations in space.

Ax Sheng-You Chien, Bo-Yi Mao, Yi-Ning Chang, Po-Chih Kuo 4/7/2026

Measuring Robustness of Speech Recognition from MEG Signals Under Distribution Shift

Comparison of CNN and CNN-Transformer models for robust speech recognition from MEG brain signals under distribution shift using LibriBrain benchmark.

Ax Linglingzhi Zhu, Wentao Ding, Shangyuan Liu, Anthony Man-Cho So 4/7/2026

Primal-Dual Methods for Nonsmooth Nonconvex Optimization with Orthogonality Constraints

Mathematical framework for primal-dual optimization methods handling nonsmooth nonconvex problems with orthogonality constraints on Stiefel manifolds.

Ax Sofiane Bouaziz, Adel Hafiane, Raphael Canals, Rachid Nedjai 4/7/2026

Uncertainty-Aware Test-Time Adaptation for Cross-Region Spatio-Temporal Fusion of Land Surface Temperature

Test-time adaptation approach for improving deep learning model generalization across geographic regions in remote sensing land surface temperature prediction.

Ax Gunn Kim 4/7/2026

Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning

Framework using non-equilibrium stochastic dynamics to address stability-plasticity dilemma in continual learning via Kramers escape theory.

Ax Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta 4/7/2026

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

First comprehensive benchmark for evaluating AI models on professional graphic design tasks including layout, typography, and design intent translation.

Ax Kamyar Barakati, Boris N. Slautin, Utkarsh Pratiush, Hiroshi Funakubo, Sergei V. Kalinin 4/7/2026

PATHFINDER: Multi-objective discovery in structural and spectral spaces

ML-driven workflow for multi-objective discovery in materials science using automated microscopy and characterization, avoiding premature convergence.

Ax Mir Tafseer Nayeem, Davood Rafiei 4/7/2026

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

Study analyzing bias toward American English in LLMs through postcolonial lens, examining how data curation and geopolitical histories shape model development.

Ax Soham Bonnerjee, Zhipeng Lou, Wei Biao Wu 4/7/2026

Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization

Asymptotic convergence analysis of Q-learning with linear decay to zero learning rates addressing persistent bias and slow convergence issues.

Ax Oluseyi Olukola, Nick Rahimi 4/7/2026

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems

Formal framework and metrics for pedagogical safety in educational reinforcement learning, introducing Reward Hacking Severity Index to detect misalignment.

Ax Shuang Gao, Peter E. Caines 4/7/2026

Transmission Neural Networks: Inhibitory and Excitatory Connections

Extension of transmission neural network model incorporating inhibitory connections and neurotransmitter populations with firing probability characterization.

Ax Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez 4/7/2026

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Combee framework for scaling prompt learning in LLM agents enabling efficient self-improvement through system prompt optimization across parallel runs.

Ax Oluseyi Olukola, Nick Rahimi 4/7/2026

MC-CPO: Mastery-Conditioned Constrained Policy Optimization

MC-CPO method for constrained reinforcement learning in tutoring systems preventing reward hacking through mastery-conditioned safety constraints.

Ax Zilu Zhao, Jichao Chen, Dirk Slock 4/7/2026

Avoiding Non-Integrable Beliefs in Expectation Propagation

Theoretical work on Expectation Propagation convergence avoiding non-integrable beliefs and optimizing constrained Bethe Free Energy.

Ax Anushree Sinha, Srivaths Ranganathan, Debanshu Das, Abhishek Dharmaratnakar 4/7/2026

Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Position paper analyzing failure modes in agentic IR systems where early errors cascade despite linguistic fluency, causing misalignment between reasoning and execution.

Ax Ioannis Panitsas, Leandros Tassiulas 4/7/2026

A Family of Open Time-Series Foundation Models for the Radio Access Network

Open foundation models for Radio Access Network time-series forecasting enabling AI-native optimization and closed-loop control with improved generalization.

Ax Yash Ganpat Sawant 4/7/2026

High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making

System and analysis of personalized LLM customization for individual investor decision-making, identifying fundamental limitations in current personalization paradigms.

Ax Seyed Mohammad Azimi-Abarghouyi 4/7/2026

Out-of-Air Computation: Enabling Structured Extraction from Wireless Superposition

Out-of-air computation framework for structured extraction from wireless superposition using joint source-channel coding without pre-embedded computation.

Ax Edward Hirst, Henrique N. S\'a Earp, Tom\'as S. R. Silva 4/7/2026

Minimising Willmore Energy via Neural Flow

Neural Willmore flow approach using neural architectures and PINN-style loss functions to minimize Willmore energy on 2D surfaces.

Ax Saad Alqithami 4/7/2026

Soft Tournament Equilibrium

Soft Tournament Equilibrium framework for evaluating LLM-based agents in non-transitive competitive settings using set-valued rankings instead of linear orderings.

Ax Sooyoung Lim, Zhenlong Li, Zi-Kui Liu 4/7/2026

Thermodynamic-Inspired Explainable GeoAI: Uncovering Regime-Dependent Mechanisms in Heterogeneous Spatial Systems

Thermodynamics-inspired GeoAI method for modeling spatial heterogeneity and critical transitions in geographic and environmental systems.

Ax Maher Al Islam, Amr S. El-Wakeel 4/7/2026

Adversarial Robustness Analysis of Cloud-Assisted Autonomous Driving Systems

Analysis of adversarial robustness in cloud-assisted autonomous driving systems with deep learning perception models and network vulnerabilities.

Ax Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, Boris Knyazev 4/7/2026

REAM: Merging Improves Pruning of Experts in LLMs

REAM method for pruning mixture-of-experts in large language models by merging experts, addressing memory challenges in deployment of billion-parameter models.

Ax Emerson Lopes Machadoa, Cristiano Jacques Miosso, Ricardo Pezzuol Jacobi 4/7/2026

Integer-Only Operations on Extreme Learning Machine Test Time Classification

Theoretical analysis of integer-only operations for extreme learning machine classifiers to reduce computational cost at test time without accuracy loss.

Ax Maohao Shen, Kaiwen Zha, Zexue He, Zhang-Wei Hong, Siru Ouyang, J. Jon Ryu, Prasanna Sattigeri, Suhas Diggavi, Gregory Wornell 4/7/2026

Decocted Experience Improves Test-Time Inference in LLM Agents

Proposes methods to improve LLM agent performance at test-time without parameter updates by optimizing inference-time computation for complex reasoning tasks.

Ax Gregory N. Frank 4/7/2026

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Identifies sparse routing mechanisms in alignment-trained LLMs using gate and amplifier heads to control refusal behavior, validated across 9 models from 6 labs.

Ax Zhimin Zhao 4/7/2026

Gradual Cognitive Externalization: From Modeling Cognition to Constituting It

Framework analyzing how ambient AI systems through causal user coupling transition from modeling to constituting part of cognitive function.

Ax Haoxin Lin, Junjie Zhou, Daheng Xu, Yang Yu 4/7/2026

ReinVBC: A Model-based Reinforcement Learning Approach to Vehicle Braking Controller

Model-based reinforcement learning approach for vehicle braking controller calibration.

Ax Tayyab Nasir, Daochang Liu, Ajmal Mian 4/7/2026

NAIMA: Semantics Aware RGB Guided Depth Super-Resolution

Research on depth map super-resolution using semantic priors and RGB guidance.

Ax Poornima Kumaresan, Shwetha Singaravelu, Lakshmi Rajendran, Santhosh Sivasubramani 4/7/2026

Eliminating Vendor Lock-In in Quantum Machine Learning via Framework-Agnostic Neural Networks

Research on framework-agnostic quantum machine learning neural networks to reduce vendor lock-in across QML platforms.

Ax Yiyao Zhang, Diksha Goel, Hussain Ahmad 4/7/2026

Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning

Research on autonomous agents using multi-agent reinforcement learning for explainable cyber defense against APT techniques.

Ax Xuyang Li, Rui Li, Teng Man, Yimin Lu 4/7/2026

Generative modeling of granular flow on inclined planes using conditional flow matching

Generative model using conditional flow matching to simulate granular flow physics on inclined planes for inverse reconstruction.

Ax Abu Noman Md Sakib, Zhensen Wang, Merjulah Roby, Zijie Zhang 4/7/2026

Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition

Research on measuring consistency of model explanations across similar inputs using attribution stability metrics for explainable AI systems.

Ax Tianmeng Fang, Yong Wang, Zetai Kong, Zengzhen Su, Jun Wang, Chengjin Yu, Wei Wang 4/7/2026

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models

Defense framework against backdoor attacks in multimodal LLMs using patch-based cross-view regularization during fine-tuning.

Ax Wei Zhou, Yue Shen, Junkai Ji, Yinglan Feng, Xing Tang, Xiuqiang He, Liang Feng, Zexuan Zhu 4/7/2026

SLSREC: Self-Supervised Contrastive Learning for Adaptive Fusion of Long- and Short-Term User Interests

Self-supervised contrastive learning framework for recommendation systems fusing long-term and short-term user interest patterns.

Ax Martin Kristjansen (Aalborg University), Kim Guldstrand Larsen (Aalborg University), Marius Miku\v{c}ionis (Aalborg University), Christian Schilling (Aalborg University) 4/7/2026

Safe and Near-Optimal Gate Control: A Case Study from the Danish West Coast

Optimization framework for automated water gate control balancing safety and performance requirements for Danish fjord management.

Ax Gitte Kremling, Jeffrey N\"af, Johannes Lederer 4/7/2026

Generative Modeling under Non-Monotonic MAR Missingness via Approximate Wasserstein Gradient Flows

FLOWGEM: Iterative generative method using Wasserstein gradient flows for data imputation with non-monotone missingness patterns.