7 papers
Efficient Test-Time Scaling for LLM-based Time Series Forecasting
Xuan-May Le, Minh-Tuan Tran, Ling Luo +3
Long-term time series forecasting benefits from preserving global structure such as trends and seasonality. Recent LLM-based forecasters often improve accuracy through test-time sc…
Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling
Minh-Tuan Tran, Xuan-May Le, Quan Hung Tran +3
Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast…
Sharpness-Aware Teleportation on Riemannian Manifolds
Tuan Truong, Hoang-Phi Nguyen, Haocheng Luo +4
Recent studies highlight the effectiveness of flat minima in enhancing generalization, with sharpness-aware minimization (SAM) achieving state-of-the-art performance. Additionally,…
Enhancing Dataset Distillation via Non-Critical Region Refinement
Minh-Tuan Tran, Trung Le, Xuan-May Le +2
Dataset distillation has become a popular method for compressing large datasets into smaller, more efficient representations while preserving critical information for model trainin…
SHIP: A Shapelet-based Approach for Interpretable Patient-Ventilator Asynchrony Detection
Xuan-May Le, Ling Luo, Uwe Aickelin +3
Patient-ventilator asynchrony (PVA) is a common and critical issue during mechanical ventilation, affecting up to 85% of patients. PVA can result in clinical complications such as…
Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation
Minh-Tuan Tran, Trung Le, Xuan-May Le +3
Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data.…