2 papers
cs.LG2026
BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
Yuhan Xie, Chen Lyu
Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original trainin…
cs.SE2025
SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code
Qinglin Wang, Zhihong Sun, Ruyun Wang +4
Large Language Models (LLMs) can translate natural language requirements into code, yet empirical analyses of representative models reveal that semantic errors-programs that compil…