Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM arxiv.org/abs/2510.20838 .AI .MA

\textsc{autoresearcher}: Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration arxiv.org/abs/2510.20844 .MA

Cultural Alien Sampler: Open-ended art generation balancing originality and coherence arxiv.org/abs/2510.20849 .AI .CL .LG

FedMicro-IDA: A Federated Learning and Microservices-based Framework for IoT Data Analytics arxiv.org/abs/2510.20852 .CR

FPT-Noise: Dynamic Scene-Aware Counterattack for Test-Time Adversarial Defense in Vision-Language Models arxiv.org/abs/2510.20856 .CR

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology arxiv.org/abs/2510.20858 .CR

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards arxiv.org/abs/2510.20867 .LG .AI

Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning arxiv.org/abs/2510.20868 .LG .AI .CE

MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions arxiv.org/abs/2510.20872 .ML .LG

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability arxiv.org/abs/2510.19851 .CR .AI

LLM Bazaar: A Service Design for Supporting Collaborative Learning with an LLM-Powered Multi-Party Collaboration Infrastructure arxiv.org/abs/2510.18877 .HC .AI

CityAQVis: Integrated ML-Visualization Sandbox Tool for Pollutant Estimation in Urban Regions Using Multi-Source Data (Software Article) arxiv.org/abs/2510.18878 .HC .LG

FIRETWIN: Digital Twin Advancing Multi-Modal Sensing, Interactive Analytics for Wildfire Response arxiv.org/abs/2510.18879 .HC

Towards Better Health Conversations: The Benefits of Context-seeking arxiv.org/abs/2510.18880 .HC .CL .CY

Detecting AI-Assisted Cheating in Online Exams through Behavior Analytics arxiv.org/abs/2510.18881 .HC .CY

Contextual Augmentation for Entity Linking using Large Language Models arxiv.org/abs/2510.18888 .CL .AI

Small Language Models Offer Significant Potential for Science Community arxiv.org/abs/2510.18890 .CL .AI

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs arxiv.org/abs/2510.18892 .CL .LG

CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation arxiv.org/abs/2510.18893 .DC .AI .SE

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.