Thang M. Pham

OverviewAI-generated summary

Thang M. Pham's research focuses on natural language understanding and the development of efficient language models. His work investigates how the sequential order of words impacts language comprehension tasks and explores methods for creating smaller, more effective language models suitable for on-device applications. Pham has also contributed to research on computer vision, specifically in areas such as video instance segmentation and image classification with explainable components. His recent publications include "Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation" (2024), "SlimLM: An Efficient Small Language Model for On-Device Document Assistance" (2025), and "A2VIS: Amodal-Aware Approach to Video Instance Segmentation" (2025).

He has collaborated with Ngan Le, Winston Bounsavy, Minh Quan Tran, and Taisei Hanyu, all from the University of Arkansas at Fayetteville, on multiple publications. Pham's scholarly output includes 18 publications with 66 citations, and an h-index of 3. His recent activity indicates ongoing engagement in his research areas.

Metrics

• h-index: 3
• Publications: 18
• Citations: 127