Huu-Thien Tran

collaborators

4 papers

cs.LG2026

$I ¨ $ -DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren +2

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can…

cs.CV2025

Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models

Thanh-Dat Truong, Huu-Thien Tran, Tran Thai Son +2

Large multimodal models (LMMs) have gained impressive performance due to their outstanding capability in various understanding tasks. However, these models still suffer from some f…

cs.CV2025

BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models

Huu-Thien Tran, Thanh-Dat Truong, Khoa Luu

Large vision-language models have become widely adopted to advance in various domains. However, developing a trustworthy system with minimal interpretable characteristics of large-…

cs.CV2025

MEX: Memory-efficient Approach to Referring Multi-Object Tracking

Huu-Thien Tran, Phuoc-Sang Pham, Thai-Son Tran +1

Referring Multi-Object Tracking (RMOT) is a relatively new concept that has rapidly gained traction as a promising research direction at the intersection of computer vision and nat…

I¨-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models

BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models

MEX: Memory-efficient Approach to Referring Multi-Object Tracking

$I ¨ $ -DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models