6 papers
RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management
Renqi Chen, Zeyin Tao, Jianming Guo +6
Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environme…
NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation
Renqi Chen, Haoyang Su, Shixiang Tang
The Segment Anything Model (SAM) has emerged as a powerful visual foundation model for image segmentation. However, adapting SAM to specific downstream tasks, such as medical and a…
DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation
Renqi Chen, Xinzhe Zheng, Haoyang Su +1
Accurate segmentation of ultrasound images is essential for reliable medical diagnoses but is challenged by poor image quality and scarce labeled data. Prior approaches have relied…
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
Haoyang Su, Renqi Chen, Shixiang Tang +10
The rapid advancement of scientific progress requires innovative tools that can accelerate knowledge discovery. Although recent AI methods, particularly large language models (LLMs…
ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor Data
Xinzhe Zheng, Sijie Ji, Jiawei Sun +3
Mental health risk is a critical global public health challenge, necessitating innovative and reliable assessment methods. With the development of large language models (LLMs), the…
AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research
Renqi Chen, Haoyang Su, Shixiang Tang +7
The Science of Science (SoS) explores the mechanisms underlying scientific discovery, and offers valuable insights for enhancing scientific efficiency and fostering innovation. Tra…