automated program repair 1large language models 1multimodal learning 1region focusing 1tool calling 1visual bug localization 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.SE2026
VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair
Jingyu Xiao, Zhongyi Zhang, Haoran Hou +4
VisualRepair is a multimodal LLM framework that classifies bug‑related images, dynamically calls specialized tools, and focuses on relevant screenshot regions to improve automated…
cs.SE2026
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan +3
Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur subs…
hep-ph2025
Universal Anomaly Detection at the LHC: Transforming Optimal Classifiers and the DDD Method
Sascha Caron, José Enrique GarcÃa Navarro, MarÃa Moreno Llácer +5
In this work, we present a novel approach to transform supervised classifiers into effective unsupervised anomaly detectors. The method we have developed, termed Discriminatory Det…