All research directions

Explainable & Efficient AI

Interpretable models and resource-efficient learning for deployable, trustworthy AI systems.

Goals

To make modern AI both understandable and practical — reducing compute cost while preserving transparency in how models reach their decisions.

Overview

This research pursues methods that improve the interpretability and efficiency of machine learning systems. It connects theoretical understanding of model behavior with algorithms that reduce training and inference cost for real-world deployment.

Key objectives

  • Develop interpretable representations and decision mechanisms
  • Reduce training and inference cost without losing accuracy
  • Enable efficient test-time scaling and adaptation
  • Connect explainability with robustness and calibration

Key topics

  • Model interpretability and transparency
  • Efficient training and inference
  • Test-time scaling and adaptation
  • Resource-constrained deployment

Papers in this direction

  • 2026

    Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval

    Huynh, TL, Wang, W, Le, T, Vu, TT, Gasevic, D, Li, YF, Do, TT

    arXiv preprint arXiv:2601.05549

  • 2026

    Efficient Test-Time Scaling for LLM-based Time Series Forecasting

    Le, XM, Tran, MT, Luo, L, Aickelin, U, Phung, D, Le, T

    Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining