Papers by Mengwei Xu
Demystifying Small Language Models for Edge Deployment (2025.acl-long)
Copied to clipboard
Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Wei Liu, Jian Luan, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu
| Challenge: | Small language models (SLMs) are a promising solution for resource-constrained devices such as smartphones and the Web of Things. |
| Approach: | They propose to use SLMs to build and optimize a set of small language models that are publicly accessible. |
| Outcome: | The proposed models outperform 7B models in general tasks, while their in-context learning capabilities remain limited and their efficiency has significant optimization potential. |
Does Chain-of-Thought Reasoning Help Mobile GUI Agents? An Empirical Study (2026.findings-acl)
Copied to clipboard
| Challenge: | Reasoning capabilities have improved vision-language models in domains like math, coding, and visual question-answering, but their impact on real-world applications remains unclear. |
| Approach: | They evaluate six pairs of VLMs by comparing their base and reasoning-enhanced versions across static and interactive benchmarks. |
| Outcome: | The reasoning-enhanced models perform better on static and interactive benchmarks than non-reasoning models. |
DroidCall: A Dataset for LLM-powered Android Intent Invocation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | We present DroidCall, the first training and testing dataset for accurate Android intent invocation. |
| Approach: | We introduce DroidCall, the first training and testing dataset for accurate Android intent invocation. |
| Outcome: | The proposed dataset provides a training and testing pipeline for Android intent invocation. |