Xing Ma — accepted AI-conference papers

2025

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning

Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li +3

EMNLP 2025

Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on simple tasks. In this work, we systematically quantify the upper bounds of LRMs under both Long-Thinking and No-Thinking

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented Dialogue

Xing Ma, Peng Zhang, Feifei Zhao

ACL 2023findings

The end-to-end task-oriented dialogue system has achieved great success in recent years. Most of these dialogue systems need to accommodate multi-domain dialogue in real-world scenarios. However, due to the high cost of dialogue data annotation and the scarcity of labeled dialogue data, existing met…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗