Wenrui Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Wenrui Lu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Bufang Yang
The Chinese University of Hong Kong, Hong Kong, Hong Kong
4 shared publications - Guoliang Xing
The Chinese University of Hong Kong, Hong Kong SAR, China
4 shared publications - Mu Yuan
The Chinese University of Hong Kong, Hongkong, China
3 shared publications - Wei Gao
University of Pittsburgh, Pittsburgh, USA
3 shared publications - Zhenyu Yan
The Chinese University of Hong Kong, Hong Kong SAR, China
3 shared publications - Siyang Jiang
The Chinese University of Hong Kong, Hong Kong, Hong Kong
2 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1574-1576
WIP: AMAS: An Android Macro Action System for Efficient LLM Mobile Agents
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1574-1576
Open AccessWIP: AMAS: An Android Macro Action System for Efficient LLM Mobile Agents
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 156-158
Demo: Mobile RouteJump: An Efficient Mobile Agent with Vision–XML Routing and Macro Actions
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 156-158
Open AccessDemo: Mobile RouteJump: An Efficient Mobile Agent with Vision–XML Routing and Macro Actions
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 352-370
A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Multimodal human action recognition (HAR) utilizes complementary data for activity classification. Built on traditional HAR tasks, recent advances in Large Language Models (LLMs) enable detailed descriptions and causal reasoning of human actions, advancing new tasks of human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially multimodal Large Vision-Language Models (LVLMs), struggle with modalities other than RGB images, like depth, IMU, ormmWave, due to a lack of large-scale datasets in these task domains. Existing HAR datasets provide only coarse-grained annotations, in-sufficient for depicting the detailed action dynamics required in HAU and HARn tasks. Simply combining annotations and generating captions with LLMs often lacks necessary logical and spatiotemporal consistency. In this paper, we introduce CUHK-X, a large-scale multi-modal dataset and benchmarks for HAR, HAU, and HARn. It includes 64,267 samples of 40 actions performed by 30 participants across two indoor environments, covering diverse daily scenarios. To address the challenge of spatiotemporal inconsistencies in captions, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences. CUHK-X also includes three benchmarks with six tasks to evaluate state-of-the-art models. Experimental results show average accuracies of 76.52% for HAR, 40.76% for HAU, and 70.25% for HARn. This large-scale multimodal dataset aims to empower the research community to apply, develop, and adapt data-intensive learning techniques for a wide range of human activity-related tasks.
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 352-370
Open AccessA Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Multimodal human action recognition (HAR) utilizes complementary data for activity classification. Built on traditional HAR tasks, recent advances in Large Language Models (LLMs) enable detailed descriptions and causal reasoning of human actions, advancing new tasks of human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially multimodal Large Vision-Language Models (LVLMs), struggle with modalities other than RGB images, like depth, IMU, ormmWave, due to a lack of large-scale datasets in these task domains. Existing HAR datasets provide only coarse-grained annotations, in-sufficient for depicting the detailed action dynamics required in HAU and HARn tasks. Simply combining annotations and generating captions with LLMs often lacks necessary logical and spatiotemporal consistency. In this paper, we introduce CUHK-X, a large-scale multi-modal dataset and benchmarks for HAR, HAU, and HARn. It includes 64,267 samples of 40 actions performed by 30 participants across two indoor environments, covering diverse daily scenarios. To address the challenge of spatiotemporal inconsistencies in captions, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences. CUHK-X also includes three benchmarks with six tasks to evaluate state-of-the-art models. Experimental results show average accuracies of 76.52% for HAR, 40.76% for HAU, and 70.25% for HARn. This large-scale multimodal dataset aims to empower the research community to apply, develop, and adapt data-intensive learning techniques for a wide range of human activity-related tasks.
- Open Access
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 21-25
DIMGen: Dynamic Intent Macro Generation for Efficient LLM-Driven Mobile Automation
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 21-25
Open AccessDIMGen: Dynamic Intent Macro Generation for Efficient LLM-Driven Mobile Automation
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 163-176
Mozart: A Mobile ToF System for Sensing in the Dark through Phase Manipulation
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 163-176
Open AccessMozart: A Mobile ToF System for Sensing in the Dark through Phase Manipulation