RE-MMNAS: LLM Reasoning-Guided Evolutionary Architecture Search for Multi-Modal Feature Fusion
Haowen Xiao, Xueming Yan, Yue Hong Xie, Han Pang Huang
South China University of Technology Guangdong University of Foreign Studies Loughborough University Sun Yat-sen University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Multi-modal neural architecture search faces two fundamental challenges: semantic misalignment across heterogeneous feature scales and modality imbalance during fusion. While traditional evolutionary methods rely on blind heuristic search, recent LLM-assisted NAS approaches treat language models as static code generators, failing to exploit their capacity for reflective reasoning. We propose RE-MMNAS, a reasoning-guided evolutionary framework that embeds LLMs as active optimization agents throughout the search loop. By performing contrastive analysis on historical architecture populations, RE-MMNAS drives two novel operators. The modality-aware crossover identifies and corrects modality imbalance via per-modality F1 scores, while the context-aware mutation is conditioned on iteratively refined evolutionary experience encoded in dynamic chain-of-thought prompts. Evaluated on MM-IMDB and EgoGesture, RE-MMNAS achieves 64.22% weighted-F1 and 95.44% accuracy, outperforming state-of-the-art baselines while discovering architectures with up to 35% fewer parameters. Ablation studies confirm that the synergy between the proposed operators and dynamic prompting is essential—neither component alone surpasses the non-LLM baseline.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIEvolutionary Algorithms and Applications
Advanced Neural Network Applications · Multimodal Machine Learning Applications