← Search

Zehui Lin

2 accepted papers

2026

S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

AAAI 2026technical

Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as mixture-of-experts, typically operate at the task level; they

Cited by 0SourcePDFScholar
2021

Learning Language Specific Sub-network for Multilingual Machine Translation

ACL 2021long

Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS…