Multimodal 2025

3 papers
The 2025 edition of Multimodal featured research focused on the application of multi-modal systems across diverse domains, including education, aviation, and urban infrastructure. Key themes included the integration of mixed reality into blended learning environments to promote sustainability concepts and the development of multi-modal dynamic depth networks for monitoring human cognitive states. Specifically, one study examined the effectiveness of game design in educational settings, while another addressed the detection of attention states in flight trainees. Additional research explored the safety implications of traffic speed characteristics on urban arterials during off-peak hours. Prolific contributors to the year's proceedings included authors such as Chenxi Xiao, Pengwei Hsiao, Zhengqing Wang, and Changyuan Wang, alongside Gongpu Wu, Guangyi Jiang, Julia Yan, Sixuan Xu, and X.X. Xie. The work presented reflects a trend toward utilizing multi-modal data and technologies to address practical challenges in safety, training, and pedagogical design.

Top Research Directions

The 11 research directions with Multimodal 2025 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Bridging the Gap Between Intention and Action133.3%
2Bridging the Simulation to Reality Gap133.3%
3Causal Attribution Challenges in Single Arm Trials133.3%
4Cross-Modal Attention for Deep Multimodal Fusion133.3%
5Cross-Modal Attention Fusion for Heterogeneous Data Integration133.3%
6Decomposing Spatiotemporal Convolutions for Efficient Video Learning133.3%
7Hybrid Convolutional Recurrent Architectures for Sequence Modeling133.3%
8Hybrid Pedagogical Architectures for Cognitive Task Decoupling133.3%
9Immersive Virtual Environments for Contextualized Learning133.3%
10The Mechanics of Qualitative and Quantitative Data Integration133.3%
11The Sustainability Gap in Short-Term Clinical Evaluations133.3%

Download all directions as CSV

Institutions

Institutions credited by Multimodal 2025 papers: a paper credits every institution named in its affiliations, once. 2 institutions share 2 credited papers.

#InstitutionPapersShare
1Macao Polytechnic University 150.0%
2Xi'an Technological University 150.0%

Download all institutions as CSV

About this data

Papers. Multimodal 2025 lists 3 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 2 of 3 papers (66.7%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Multimodal 2025”, https://lacuna.tiptreesystems.com/venue/multimodal/2025.

Top Authors

AuthorPapers
Chenxi Xiao1

Papers

Title
Mixed Reality Game Design for the Effectiveness and Application Research of Integrating Sustainable Concepts into Blended Learning
On the safety effects of off-peak hour speed characteristics of urban arterials
Research on the Detection Method of Flight Trainees’ Attention State Based on Multi-Modal Dynamic Depth Network