2 papers
cs.LG2026
Bridging the Compression-Precision Paradox: A Hybrid Architecture for Clinical EEG Report Generation with Guaranteed Measurement Accuracy
Wuyang Zhang, Zhen Luo, Chuqiao Gu +4
Automated EEG monitoring requires clinician-level precision for seizure detection and reporting. Clinical EEG recordings exceed LLM context windows, requiring extreme compression (…
cs.SE2025
SemanticForge: Repository-Level Code Generation through Semantic Knowledge Graphs and Constraint Satisfaction
Wuyang Zhang, Chenkai Zhang, Zhen Luo +4
Large language models (LLMs) have transformed software development by enabling automated code generation, yet they frequently suffer from systematic errors that limit practical dep…