5 papers
Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models
Guoyan Wang, Yanyan Huang, Chunlin Chen +2
Cross-platform strategy game automation remains a challenge due to diverse user interfaces and dynamic battlefield environments. Existing Vision--Language Models (VLMs) struggle wi…
Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
Lincan Li, Bolin Shen, Chenxi Zhao +4
Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art grap…
AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Manager
Xuhua Zhao, Yuxuan Xie, Caihua Chen +1
Recent advances in mathematical reasoning and the long-term planning capabilities of large language models (LLMs) have precipitated the development of agents, which are being incre…
Empowering Tabular Data Preparation with Language Models: Why and How?
Mengshi Chen, Yuxiang Sun, Tengchao Li +5
Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing…
Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis
Bowen Zhang, Ying Chen, Long Bai +5
Foundation models have become prominent in computer vision, achieving notable success in various tasks. However, their effectiveness largely depends on pre-training with extensive…