11 citations · 18 across the 27 of their papers we have counts for
28 papers
Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
Hieu Trung Nguyen, Bao Nguyen, Wenao Ma +3
Sampling efficiency is a key bottleneck in reinforcement learning with verifiable rewards. Existing group-based policy optimization methods, such as GRPO, allocate a fixed number o…
Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
Tung Quoc Le, Anh Tuan Nguyen, Viet Anh Nguyen
Data-driven algorithm design automates hyperparameter tuning, but its statistical foundations remain limited because model performance can depend on hyperparameters in implicit and…
Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
Dongxuan Zhu, Ly Tran Ho Khanh, Andy Yat-Ming Cheung +2
Language models often default to a narrow set of high-probability outputs, leaving their generation paths homogeneous and prone to mode collapse. Sampling-based strategies inject r…
SCOPE: Spectral Concentration by Distributionally Robust Joint Covariance-Precision Estimation
Renjie Chen, Viet Anh Nguyen, Huifu Xu
We propose a distributionally robust formulation for simultaneously estimating the covariance matrix and the precision matrix of a random vector.The proposed model minimizes the wo…
Test-time Diverse Reasoning by Riemannian Activation Steering
Ly Tran Ho Khanh, Dongxuan Zhu, Man-Chung Yue +1
Best-of- reasoning improves the accuracy of language models in solving complex tasks by sampling multiple candidate solutions and then selecting the best one based on some crite…
Reasoning Planning for Language Models
Bao Nguyen, Hieu Trung Nguyen, Ruifeng She +2
Selecting an appropriate reasoning method for a given query remains a key challenge in language model generation. Existing approaches typically generate multiple candidate response…
CGCE: Classifier-Guided Concept Erasure in Generative Models
Viet Nguyen, Vishal M. Patel
Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the gen…
Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
Quan Dao, Xiaoxiao He, Ligong Han +6
Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation…
Provably data-driven projection method for quadratic programming
Anh Tuan Nguyen, Viet Anh Nguyen
Projection methods aim to reduce the dimensionality of the optimization instance, thereby improving the scalability of high-dimensional problems. Recently, Sakaue and Oki proposed…
Structured Pruning for Diverse Best-of-N Reasoning Optimization
Hieu Trung Nguyen, Bao Nguyen, Viet Anh Nguyen
Model pruning in transformer-based language models, traditionally viewed as a means of achieving computational savings, can enhance the model's reasoning capabilities. In this work…
PDF Retrieval Augmented Question Answering
Thi Thu Uyen Hoang, Meenakshi Rajendran, Kun Zhang +2
This paper presents an advancement in Question-Answering (QA) systems using a Retrieval Augmented Generation (RAG) framework to enhance information extraction from PDF files. Recog…
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
Viet-Anh Nguyen, Shiqian Zhao, Gia Dao +3
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite…
Mixture-of-Personas Language Models for Population Simulation
Ngoc Bui, Hieu Trung Nguyen, Shantanu Kumar +4
Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-genera…
Task-driven Layerwise Additive Activation Intervention
Hieu Trung Nguyen, Bao Nguyen, Binh Nguyen +1
Modern language models (LMs) have significantly advanced generative modeling in natural language processing (NLP). Despite their success, LMs often struggle with adaptation to new…
Probe-Free Low-Rank Activation Intervention
Chonghe Jiang, Bao Nguyen, Anthony Man-Cho So +1
Language models (LMs) can produce texts that appear accurate and coherent but contain untruthful or toxic content. Inference-time interventions that edit the hidden activations hav…
Distributional Surgery for Language Model Activations
Bao Nguyen, Binh Nguyen, Duy Nguyen +1
Language models, while capable of generating remarkably coherent and seemingly accurate text, can occasionally produce undesirable content, including harmful or toxic outputs. In t…
Asymptotically Optimal Distributionally Robust Solutions through Forecasting and Operations Decentralization
Yue Lin, Daniel Zhuoyu Long, Viet Anh Nguyen +1
Two-stage risk-averse distributionally robust optimization (DRO) problems are ubiquitous across many engineering and business applications. Despite their promising resilience, two-…
Generative Conditional Distributions by Neural (Entropic) Optimal Transport
Bao Nguyen, Binh Nguyen, Hieu Trung Nguyen +1
Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the c…
Cold-start Recommendation by Personalized Embedding Region Elicitation
Hieu Trung Nguyen, Duy Nguyen, Khoa Doan +1
Rating elicitation is a success element for recommender systems to perform well at cold-starting, in which the systems need to recommend items to a newly arrived user with no prior…
Retrospective Feature Estimation for Continual Learning
Nghia D. Nguyen, Hieu Trung Nguyen, Ang Li +3
The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, wh…
Explaining Graph Neural Networks via Structure-aware Interaction Index
Ngoc Bui, Hieu Trung Nguyen, Viet Anh Nguyen +1
The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, su…
Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation
Duy Nguyen, Bao Nguyen, Viet Anh Nguyen
Algorithmic recourse recommends a cost-efficient action to a subject to reverse an unfavorable machine learning classification decision. Most existing methods in the literature gen…
Bellman Optimal Stepsize Straightening of Flow-Matching Models
Bao Nguyen, Binh Nguyen, Viet Anh Nguyen
Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these…
Coverage-Validity-Aware Algorithmic Recourse
Ngoc Bui, Duy Nguyen, Man-Chung Yue +1
Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency, and ethics of machine learning models. Existing algorithmic recourse approaches o…