5 citations · 21 across the 22 of their papers we have counts for
26 papers
Kernelized Activation Steering
Laziz U. Abdullaev, Minh-Hieu Pham, Bach Do +2
Activation steering provides a simple, training-free mechanism for controlling attributes of generative models such as sentiment, style, and helpfulness. However, standard approach…
Reservoir of Importance: Learning Semi-Structured Sparsity with Differentiable Subset Sampling
Ha Dinh, Xuan Duy Ta, Khoat Than +1
Semi-structured : sparsity has emerged as a practical direction for accelerating large language models (LLMs). However, existing learnable-mask approaches incur substantial p…
No-Free-Fairness: Fundamental Limits and Trade-offs in Learning Systems
Khoat Than
In this paper, we establish a set of theoretical impossibility results, termed the No-Free-Fairness theorems, that identify three fundamental sources of disparity in learning syste…
High-Dimensional Random Projection for Activation Steering in Language Models
Minh-Hieu Pham, Bach Do, Laziz Abdullaev +2
Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs). Existing difference-in-means based methods, however, are fundamen…
LCA: Local Classifier Alignment for Continual Learning
Tung Tran, Danilo Vasconcellos Vargas, Khoat Than
A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastr…
Using Synthetic Data to estimate the True Error is theoretically and practically doable
Hai Hoang Thanh, Duy-Tung Nguyen, Hung The Tran +1
Accurately evaluating model performance is crucial for deploying machine learning systems in real-world applications. Traditional methods often require a sufficiently large labeled…
The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control
Khoat Than
Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to stabilize training dynamics and improve ge…
Provably Improving Generalization of Few-Shot Models with Synthetic Data
Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh +3
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate…
Enhancing Visual Feature Attribution via Weighted Integrated Gradients
Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang +2
Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key…
Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models
Khoat Than, Dat Phan
Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning. We introduce a new class of data-dependent ge…
Gentle Local Robustness implies Generalization
Khoat Than, Dat Phan, Giang Vu
Robustness and generalization ability of machine learning models are of utmost importance in various application domains. There is a wide interest in efficient ways to analyze thos…
On Inference Stability for Diffusion Models
Viet Nguyen, Giang Vu, Tung Nguyen Thanh +2
Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training met…
KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
Quyen Tran, Hoang Phan, Lam Tran +4
Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field o…
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
Quyen Tran, Hai Nguyen, Hoang Phan +6
In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because previous samples have limited replay valu…
Face Swapping as A Simple Arithmetic Operation
Truong Vu, Kien Do, Khang Nguyen +1
We propose a novel high-fidelity face swapping method called "Arithmetic Face Swapping" (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN…
From Implicit to Explicit feedback: A deep neural network for modeling sequential behaviours and long-short term preferences of online users
Quyen Tran, Lam Tran, Linh Chu Hai +2
In this work, we examine the advantages of using multiple types of behaviour in recommendation systems. Intuitively, each user has to do some implicit actions (e.g., click) before…
Generalization of GANs and overparameterized models under Lipschitz continuity
Khoat Than, Nghia Vu
Generative adversarial networks (GANs) are so complex that the existing learning theories do not provide a satisfactory explanation for why GANs have great success in practice. The…
Structured Dropout Variational Inference for Bayesian Neural Networks
Son Nguyen, Duong Nguyen, Khai Nguyen +3
Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability…
Bag of biterms modeling for short texts
Anh Phan Tuan, Bach Tran, Thien Nguyen Huu +2
Analyzing texts from social media encounters many challenges due to their unique characteristics of shortness, massiveness, and dynamic. Short texts do not provide enough context i…
Predictive Coding for Locally-Linear Control
Rui Shu, Tung Nguyen, Yinlam Chow +5
High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks. The Learning Controllable Embedding…
Dynamic transformation of prior knowledge into Bayesian models for data streams
Tran Xuan Bach, Nguyen Duc Anh, Ngo Van Linh +1
We consider how to effectively use prior knowledge when learning a Bayesian model from streaming environments where the data come infinitely and sequentially. This problem is highl…
A Graph Convolutional Topic Model for Short and Noisy Text Streams
Ngo Van Linh, Tran Xuan Bach, Khoat Than
Learning hidden topics from data streams has become absolutely necessary but posed challenging problems such as concept drift as well as short and noisy data. Using prior knowledge…
Inference in topic models: sparsity and trade-off
Khoat Than, Tu Bao Ho
Topic models are popular for modeling discrete data (e.g., texts, images, videos, links), and provide an efficient way to discover hidden structures/semantics in massive data. One…
Guaranteed inference in topic models
Khoat Than, Tung Doan
One of the core problems in statistical models is the estimation of a posterior distribution. For topic models, the problem of posterior inference for individual texts is particula…