3 papers
cs.SE2026
GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
Zhuoyao Liu, Zhengran Zeng, Shu-Dong Huang +3
Large Language Model (LLM)-based Automated Program Repair (APR) has shown strong potential on textual benchmarks, yet struggles in multimodal scenarios where bugs are reported with…
cs.CV2025
PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
Zhuoyao Liu, Yang Liu, Wentao Feng +1
Cross-modal retrieval aims to align different modalities via semantic similarity. However, existing methods often assume that image-text pairs are perfectly aligned, overlooking No…
cs.CV2025
Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching
Yang Liu, Wentao Feng, Zhuoyao Liu +2
Enabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge. Existing methods typically learn a set of embeddings to fin…