3 citations · 11 across the 38 of their papers we have counts for
16 papers · 1 filter
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
Tuan Nguyen, Qiran Hu, Banruo Liu +3
Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved documents, but longer contexts inc…
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan +2
Backdoor attacks on molecular graph neural networks (GNNs) are typically evaluated as abstract graph edits, but real molecular learning pipelines do not train on arbitrary graphs.…
When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning
Thinh T. H. Nguyen, Khoa D. Doan, Binh T. Nguyen +2
Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at different stages, and provide uneve…
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road
Ngoc-Hieu Nguyen, Parshin Shojaee, Phuc Minh Nguyen +4
Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedur…
Decoding the Critique Mechanism in Large Reasoning Models
Hoang Phan, Quang H. Nguyen, Hung T. Q. Le +3
Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong perfo…
HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
Thinh Nguyen, Trung Phan, Binh T. Nguyen +2
Federated Learning (FL) is a decentralized approach where multiple clients collaboratively train a shared global model without sharing their raw data. Despite its effectiveness, co…
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
Thinh Nguyen, Le Huy Khiem, Van-Tuan Tran +3
Federated Learning (FL) enables collaborative training across distributed clients without sharing raw data, offering strong privacy benefits. However, most methods assume all clien…
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
Tuan Nguyen, Sze Jue Yang, Khoa D. Doan +2
Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test. Such…
Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
Phuc Minh Nguyen, Ngoc-Hieu Nguyen, Duy H. M. Nguyen +5
Direct Alignment Algorithms (DAAs) such as Direct Preference Optimization (DPO) have emerged as alternatives to the standard Reinforcement Learning from Human Feedback (RLHF) for a…
Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimation
Duy A. Nguyen, Quan Huu Do, Khoa D. Doan +1
Multimodal learning has demonstrated incredible successes by integrating diverse data sources, yet it often relies on the availability of all modalities - an assumption that rarely…
Flatness-aware Sequential Learning Generates Resilient Backdoors
Hoang Pham, The-Anh Ta, Anh Tran +1
Recently, backdoor attacks have become an emerging threat to the security of machine learning models. From the adversary's perspective, the implanted backdoors should be resistant…
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
Quang H. Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta +4
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clea…
Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
Thinh Nguyen, Khoa D Doan, Binh T. Nguyen +2
Federated Class-Incremental Learning (FCIL) increasingly becomes important in the decentralized setting, where it enables multiple participants to collaboratively train a global mo…
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
Quang H. Nguyen, Thinh Dao, Duy C. Hoang +4
The rapid progress in machine learning (ML) has brought forth many large language models (LLMs) that excel in various tasks and areas. These LLMs come with different abilities and…
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…
A Cosine Similarity-based Method for Out-of-Distribution Detection
Nguyen Ngoc-Hieu, Nguyen Hung-Quang, The-Anh Ta +3
The ability to detect OOD data is a crucial aspect of practical machine learning applications. In this work, we show that cosine similarity between the test feature and the typical…