2 citations · 5 across the 9 of their papers we have counts for
10 papers
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining.…
Fast Model Selection and Stable Optimization for Softmax-Gated Multinomial-Logistic Mixture of Experts Models
TrungKhang Tran, TrungTin Nguyen, Md Abul Bashar +3
Mixture-of-Experts (MoE) architectures combine specialized predictors through a learned gate and are effective across regression and classification, but for classification with sof…
Sparse classification with positive-confidence data in high dimensions
The Tien Mai, Mai Anh Nguyen, Trung Nghia Nguyen
High-dimensional learning problems, where the number of features exceeds the sample size, often require sparse regularization for effective prediction and variable selection. While…
Model Selection for Gaussian-gated Gaussian Mixture of Experts Using Dendrograms of Mixing Measures
Tuan Thai, TrungTin Nguyen, Dat Do +2
Mixture of Experts (MoE) models constitute a widely utilized class of ensemble learning approaches in statistics and machine learning, known for their flexibility and computational…
A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random
Binh H. Ho, Long Nguyen Chi, TrungTin Nguyen +3
Model-based clustering integrated with variable selection is a powerful tool for uncovering latent structures within complex data. However, its effectiveness is often hindered by c…
Near-Polynomially Competitive Active Logistic Regression
Yihan Zhou, Eric Price, Trung Nguyen
We address the problem of active logistic regression in the realizable setting. It is well known that active learning can require exponentially fewer label queries compared to pass…
Accelerating Transformers with Spectrum-Preserving Token Merging
Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen +7
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an…
CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Quang Pham, Giang Do, Huy Nguyen +8
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, effective traini…
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
Duy M. H. Nguyen, Nina Lukashina, Tai Nguyen +7
A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and c…
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
Giang Do, Khiem Le, Quang Pham +7
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the rout…