activity
20242026
collaborators

6 papers

cs.CL2026

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

Kun Huang, Weikai Xu, Yuxuan Liu +6

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse…

cs.CL2026

TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation

Renren Jin, Tianhao Shen, Xinwei Wu +9

Conducting supervised and preference fine-tuning of large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human…

cs.CL2026

Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents

Weikai Xu, Zhizheng Jiang, Yuxuan Liu +7

VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to complete daily tasks. However, existing…

cs.CL2025

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization

Dingyu Yao, Bowen Shen, Zheng Lin +4

The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV…

cs.CL2025

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation

Qinzhuo Wu, Wei Liu, Jian Luan +1

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solv…

cs.CL2024

DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models

Xiaolin Hu, Xiang Cheng, Peiyu Liu +4

Low-rank adaptation (LoRA) reduces the computational and memory demands of fine-tuning large language models (LLMs) by approximating updates with low-rank matrices. However, low-ra…