Ax Lirong Che, Zhenfeng Gan, Yanbo Chen, Junbo Tan, Xueqian Wang 3/25/2026

PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding

Embodied AI agent integrating multimodal LLMs with chain-of-thought reasoning for robotic photography tasks.

Ax Mincheol Kwon, Minseung Lee, Seonga Choi, Miso Choi, Kyeong-Jin Oh, Hyunyoung Lee, Cheonyoung Park, Yongho Song, Seunghyun Park, Jinkyu Kim 3/25/2026

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

PinPoint method for identifying instruction-relevant image regions in VLMs to reduce computational overhead.

Ax Abhinaba Basu, Pavan Chakraborty 3/25/2026

When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning

Study evaluating whether frontier LLMs genuinely use reasoning steps or generate decorative narratives post-hoc.

Ax Chunxia Qin, Chenyu Liu, Pengcheng Xia, Jun Du, Baocai Yin, Bing Yin, Cong Liu 3/25/2026

TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment

End-to-end table recognition method with detail-aware learning and cell-level visual alignment.

Ax Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao Li 3/25/2026

URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

Uncertainty-integrated neural network for unsupervised anomaly detection in industrial and medical imaging.

Ax Jun Yang, Dong Wang, Hongxu Yin, Hongpeng Li, Jianxiong Yu 3/25/2026

UAV-DETR: DETR for Anti-Drone Target Detection

DETR-based object detection framework for miniature drone detection in complex environments.

Ax Haiyue Zhang, Yi Nian, Yue Zhao 3/25/2026

Agent Audit: A Security Analysis System for LLM Agent Applications

Security analysis framework for LLM agent deployments covering model, tool code, credentials, and MCP configurations.

Ax Chaoqun Cui, Caiyan Jia 3/25/2026

Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer

GNN method addressing over-smoothing in rumor detection on social media propagation trees using transformer architecture.

Ax Abhinaba Basu 3/25/2026

The Coordinate System Problem in Persistent Structural Memory for Neural Architectures

Dual-View Pheromone Pathway Network (DPPN) architecture for persistent structural memory in neural networks. Identifies coordinate system requirements.

Ax Rohan Sequeira, Stavros Damianakis, Umar Iqbal, Konstantinos Psounis 3/25/2026

Agent-Sentry: Bounding LLM Agents via Execution Provenance

Agent-Sentry: Security system for bounding LLM agents via execution provenance tracking. Addresses safety and security concerns in agentic systems.

Ax Ruixing Jin, Zicheng Zhu, Ruixiang Ouyang, Sheng Xu, Bo Yue, Zhizheng Wu, Guiliang Liu 3/25/2026

Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models

Empirical study of sim-to-real transfer for robotic dexterous manipulation using vision-language-action models. Addresses synthetic-to-real gap.

Ax Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu 3/25/2026

Confidence Calibration under Ambiguous Ground Truth

Shows that confidence calibration fails when annotator disagreement exists. Proposes calibration against annotator distribution rather than majority labels.

Ax Kohsuke Kubota, Mitsuhiro Takahashi, Yuta Saito 3/25/2026

Off-Policy Evaluation and Learning for Survival Outcomes under Censoring

Off-policy evaluation framework for optimizing survival outcomes with right-censored data. Applied to healthcare and retention decisions.

Ax Shaobo Ju, Baiyang Song, Tao Chen, Jiapeng Zhang, Qiong Wu, Chao Chang, HuaiXi Wang, Yiyi Zhou, Rongrong Ji 3/25/2026

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

ForestPrune: Training-free token compression for video MLLMs using spatial-temporal modeling. Achieves high-ratio compression for video processing.

Ax Georgios Pavlidis 3/25/2026

From the AI Act to a European AI Agency: Completing the Union's Regulatory Architecture

Discussion of EU AI Act implementation and proposed European AI Agency for regulatory oversight and governance. Policy focused.

Ax Yaolun Zhang, Ruohui Wang, Jiahao Wang, Yepeng Tang, Xuanyu Zheng, Haonan Duan, Hao Lu, Hanming Deng, Lewei Lu 3/25/2026

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

EVA: Reinforcement learning method for video understanding agents using multimodal LLMs. Adaptive frame sampling and reasoning without manual workflows.

Ax Ye Li, Anqi Hu, Yuanchang Ye, Shiyan Tong, Zhiyuan Wang, Bo Fu 3/25/2026

Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees

Method for LLMs to return set-valued predictions with coverage guarantees instead of single outputs. Improves answer discovery through repeated sampling.

Ax Jawid Ahmad Baktash, Mosa Ebrahimi, Mohammad Zarif Joya, Mursal Dawodi 3/25/2026

DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube

Dataset of 9,224 Dari-language YouTube videos labeled for misinformation detection and harm levels. Addresses gap in non-English misinformation research.

Ax Benjamin Gutteridge, Michael Bronstein, Xiaowen Dong 3/25/2026

Can Graph Foundation Models Generalize Over Architecture?

Graph foundation models tested for zero-shot generalization across different GNN architectures and scales.

Ax Yutao Luo, Haotian Zhu, Shuchao Pang, Zhigang Lu, Tian Dong, Yongbin Zhou, Minhui Xue 3/25/2026

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

Visual backdoor attacks exploit mobile GUI agents via notification-based remote action execution.

Ax Davide Scassola, Dylan Ponsford, Adri\'an Javaloy, Sebastiano Saccani, Luca Bortolussi, Henry Gouk, Antonio Vergari 3/25/2026

A Sobering Look at Tabular Data Generation via Probabilistic Circuits

Tabular data generation via probabilistic circuits questioned; current benchmarks overstated progress.

Ax Samar Heydari, Jawher Said, Galip \"Umit Yolcu, Evgenii Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios Mygdalis, Ioannis Pitas, Sebastian Lapuschkin, Leila Arras 3/25/2026

Concept-based explanations of Segmentation and Detection models in Natural Disaster Management

Concept-based explainability framework for flood/wildfire detection models in disaster management.

Ax ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun, Gilhan Park, WonJun Moon, Jae-Pil Heo 3/25/2026

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation

GLA-CLIP enables training-free open-vocabulary semantic segmentation with global-local window alignment.

Ax Marios Impraimakis, Daniel Vazquez, Feiyu Zhou 3/25/2026

YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception

Kolmogorov-Arnold networks improve YOLOv10 interpretability for object detection in degraded conditions.

Ax Ant\'onio Cardoso, Pedro Sousa, Tania Pereira, H\'elder P. Oliveira 3/25/2026

HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling

Generative AI synthesizes full-range lung CT scans to address medical imaging data scarcity.

Ax Maria Conchita Agana Navarro, Geng Li, Theo Wolf, Maria Perez-Ortiz 3/25/2026

Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts

Climate foundation models tested for robustness under no-analog distribution shifts in future climate states.

Ax Julian Oestreich, Maximilian Bley, Frank Binder, Lydia M\"uller, Maksym Sydorenko, Andr\'e Alcalde 3/25/2026

Parametric Knowledge and Retrieval Behavior in RAG Fine-Tuning for Electronic Design Automation

RAG fine-tuning evaluation for EDA long-form generation with novel human evaluation metric TriFEX.

Ax Zikang Huang, Meng Ge, Tianrui Wang, Xuanchen Li, Xiaobao Wang, Longbiao Wang, Jianwu Dang 3/25/2026

MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates

MSR-HuBERT self-supervised pre-training handles multiple audio sampling rates with adaptive downsampling.

Ax Amith Nagarajan, Thomas Altman 3/25/2026

DBAutoDoc: Automated Discovery and Documentation of Undocumented Database Schemas via Statistical Analysis and Iterative LLM Refinement

DBAutoDoc automates database schema documentation combining statistical analysis with iterative LLM refinement.

Ax Tien Rahayu Tulili, Ayushi Rastogi, Andrea Capiluppi 3/25/2026

Machine Learning Models for the Early Detection of Burnout in Software Engineering: a Systematic Literature Review

Systematic literature review of ML models for early detection of burnout in software engineers.

Ax Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan, Alexander Koller 3/25/2026

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

AuthorMix uses modular layer-wise adapters for lightweight, flexible authorship style transfer with meaning preservation.

Ax Carlos Eduardo Duarte, Neil B. Harrison, Filipe Figueiredo Correia, Ademar Aguiar, Pavl\'ina Gon\c{c}alves 3/25/2026

Can an LLM Detect Instances of Microservice Infrastructure Patterns?

LLMs detect microservice architecture patterns across multiple programming languages outperforming single-language tools.

Ax Shushanta Pudasaini, Luis Miralles-Pechu\'an, David Lillis, Marisa Llorens Salvador 3/25/2026

Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy

Explainable AI analysis reveals AI-generated text detectors exploit dataset artifacts rather than genuine detection signals.

Ax Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas 3/25/2026

Robust Safety Monitoring of Language Models via Activation Watermarking

Activation watermarking technique detects adaptive adversarial attacks against LLMs attempting to evade safety monitoring.

Ax Yingzhi He, Yan Sun, Junfei Tan, Yuxin Chen, Xiaoyu Kong, Chunxu Shen, Xiang Wang, An Zhang, Tat-Seng Chua 3/25/2026

Reasoning over Semantic IDs Enhances Generative Recommendation

Semantic ID tokens enable LLM-based generative recommendation systems with efficient decoding over large item corpora.

Ax Hao Wang, Haocheng Yang, Licheng Pan, Lei Shen, Xiaoxi Li, Yinuo Wang, Zhichao Chen, Yuan Lu, Haoxuan Li, Zhouchen Lin 3/25/2026

ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment

Implicit reward modeling from human feedback like clicks for cost-effective LLM alignment via RLHF.

Ax Aomar Osmani 3/25/2026

General Machine Learning: Theory for Learning Under Variable Regimes

Foundational ML theory for learning under regime variation with evolving learner state and evaluation conditions.

Ax Chao Han, Stefanos Ioannou, Luca Manneschi, T. J. Hayward, Michael Mangan, Aditya Gilra, Eleni Vasilaki 3/25/2026

Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning

Investigation of neural ODEs and SDEs for model-based reinforcement learning, showing neural SDEs better capture stochasticity in environment dynamics.

Ax Ruisong Zhou, Haijun Zou, Li Zhou, Chumin Sun, Zaiwen Wen 3/25/2026

A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling

WeCAN: reinforcement learning framework for heterogeneous DAG scheduling addressing task compatibility, resource constraints, and rapid schedule generation.

Ax Daniele Tarchi 3/25/2026

AI Lifecycle-Aware Feasibility Framework for Split-RIC Orchestration in NTN O-RAN

AI lifecycle management for split RAN intelligent controller orchestration across non-terrestrial networks, comparing ground-centric and distributed deployment scenarios.

Ax Miao Yu, Siyuan Fu, Moayad Aloqaily, Zhenhong Zhou, Safa Otoum, Xing fan, Kun Wang, Yufei Guo, Qingsong Wen 3/25/2026

SafeSeek: Universal Attribution of Safety Circuits in Language Models

SafeSeek framework for universal attribution of safety circuits in LLMs using mechanistic interpretability to understand alignment, jailbreak, and backdoor behaviors.

Ax Wenyu Chen, Xiangtao Meng, Chuanchao Zang, Li Wang, Xinyu Gao, Jianing Wang, Peng Zhan, Zheng Li, Shanqing Guo 3/25/2026

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Query-efficient jailbreak fuzzing method for LLMs that identifies token importance during prompt mutation to reduce redundant searching under query constraints.

Ax Shaid Hasan, Breenice Lee, Sujan Sarker, Tariq Iqbal 3/25/2026

A Multimodal Framework for Human-Multi-Agent Interaction

Multimodal framework for human-multi-agent interaction integrating perception, embodied expression, and coordinated decision-making in shared physical spaces.

Ax Luca Sodano, Sofia Sciangula, Amulya Galmarini, Francesco Bertolotti 3/25/2026

Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook

Analysis of LLM-based social network where autonomous AI agents interact through natural language, studying collective dynamics and emergent network fragility.

Ax Jiaqi Dong 3/25/2026

A Comparative Study of Machine Learning Models for Hourly Forecasting of Air Temperature and Relative Humidity

Comparative study of seven machine learning models for hourly weather forecasting in complex topography, including XGBoost, LSTM, and CNN-LSTM variants.

Ax Mehmet Caner, Agostino Capponi, Nathan Sun, Jonathan Y. Tan 3/25/2026

Designing Agentic AI-Based Screening for Portfolio Investment

Agentic AI platform for portfolio investment screening using LLM agents for fundamental analysis and sentiment analysis with deliberation mechanism for buy/sell signals.

Ax V. K. Cody Bumgardner, Mitchell A. Klusty, Mahmut S. Gokmen, Evan W. Damron 3/25/2026

Curriculum-Driven 3D CT Report Generation via Language-Free Visual Grafting and Zone-Constrained Compression

Curriculum learning framework for automated radiology report generation from 3D CT volumes using Llama 3.2, addressing sequence length and class imbalance challenges.

Ax Benjamin Lange 3/25/2026

Unilateral Relationship Revision Power in Human-AI Companion Interaction

Philosophical analysis of normative implications when AI companions are updated, examining provider control and relationship structure.

Ax Hanjing Wang, S. Mostafa Mousavi, Patrick Robertson, Richard M. Allen, Alexie Barski, Robert Bosch, Nivetha Thiruverahan, Youngmin Cho, Tajinder Gadh, Steve Malkos, Boone Spooner, Greg Wimpey, Marc Stogaitis 3/25/2026

Leveraging LLMs and Social Media to Understand User Perception of Smartphone-Based Earthquake Early Warnings

Analyzes user perception of Android's Earthquake Alert system using LLMs on social media data from 2025 Türkiye earthquake.

Ax Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer, Robert J. Bainbridge, Loukas Gouskos, Benedikt Maier 3/25/2026

Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors

Proposes contrastive metric learning for point-cloud segmentation in detector systems using density-based clustering in learned metric space.