6 papers
SRA: Span Representation Alignment for Large Language Model Distillation
Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi +4
Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While exi…
Domain Transfer Becomes Identifiable via a Single Alignment
Sagar Shrestha, Subash Timilsina, Hoang-Son Nguyen +1
Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and cross-platform medical imagin…
Content-Style Identification via Differential Independence
Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1
Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors…
Learning Graph from Smooth Signals under Partial Observation: A Robustness Analysis
Hoang-Son Nguyen, Hoi-To Wai
Learning the graph underlying a networked system from nodal signals is crucial to downstream tasks in graph signal processing and machine learning. The presence of hidden nodes who…
On Detecting Low-pass Graph Signals under Partial Observations
Hoang-Son Nguyen, Hoi-To Wai
The application of graph signal processing (GSP) on partially observed graph signals with missing nodes has gained attention recently. This is because processing data from large gr…
On the Stability of Low Pass Graph Filter With a Large Number of Edge Rewires
Hoang-Son Nguyen, Yiran He, Hoi-To Wai
Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural networks (GCNs). The sta…