10 papers
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le +2
Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing d…
TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation
Tri-Nhan Vo, Dang Nguyen, Sunil Gupta
Large-scale text corpora have become a quiet bottleneck in modern NLP, not just in storage, but in the accumulated cost of training, fine-tuning, and continual learning. We propose…
Improving Diversity in Black-box Few-shot Knowledge Distillation
Tri-Nhan Vo, Dang Nguyen, Kien Do +1
Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However…
Diverse Image Priors for Black-box Data-free Knowledge Distillation
Tri-Nhan Vo, Dang Nguyen, Trung Le +2
Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI eco…
High-dimensional Level Set Estimation with Trust Regions and Double Acquisition Functions
Giang Ngo, Dat Phan Trong, Dang Nguyen +1
Level set estimation (LSE) classifies whether an unknown function's value exceeds a specified threshold for given inputs, a fundamental problem in many real-world applications. In…
Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models
Giang Ngo, Dat Phan Trong, Dang Nguyen +2
Bayesian Optimization critically depends on the choice of acquisition function, but no single strategy is universally optimal; the best choice is non-stationary and problem-depende…