12 papers
To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models
Minh-Anh Nguyen, Nguyen T. Ha Lan, Xiyan Fu +2
Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much of this degradation stems fr…
Latent Abstraction for Retrieval-Augmented Generation
Ha Lan N. T, Minh-Anh Nguyen, Dung D. Le
Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations, and improving fac…
AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
Minh-Duc Nguyen, Hai-Dang Kieu, Dung D. Le
Agentic systems powered by Large Language Models (LLMs) have shown strong potential in recommender systems but remain hindered by several challenges. Fine-tuning LLMs is parameter-…
Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion
Hai-Dang Kieu, Min Xu, Thanh Trung Huynh +1
Recent advances in multimodal recommendation (MMR) highlight the potential of integrating visual and textual content to enrich item representations. However, existing methods often…
Optimizing Electric Vehicle Charging Station Placement Using Reinforcement Learning and Agent-Based Simulations
Minh-Duc Nguyen, Dung D. Le, Phi Long Nguyen
The rapid growth of electric vehicles (EVs) necessitates the strategic placement of charging stations to optimize resource utilization and minimize user inconvenience. Reinforcemen…
SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation
Minh-Anh Nguye, Minh-Duc Nguyen, Ha Lan N. T. +3
Large language models (LLMs) are increasingly adopted for automating survey paper generation \cite{wang2406autosurvey, liang2025surveyx, yan2025surveyforge,su2025benchmarking,wen20…
A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks
Minh-Duc Nguyen, Dung D. Le
Pareto Set Learning (PSL) is popular as an efficient approach to obtaining the complete optimal solution in Multi-objective Learning (MOL). A set of optimal solutions approximates…
Enhancing News Recommendation with Hierarchical LLM Prompting
Hai-Dang Kieu, Delvin Ce Zhang, Minh Duc Nguyen +3
Personalized news recommendation systems often struggle to effectively capture the complexity of user preferences, as they rely heavily on shallow representations, such as article…
JEPA4Rec: Learning Effective Language Representations for Sequential Recommendation via Joint Embedding Predictive Architecture
Minh-Anh Nguyen, Dung D. Le
Language representation learning has emerged as a promising approach for sequential recommendation, thanks to its ability to learn generalizable representations. However, despite i…
Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks
Minh-Duc Nguyen, Phuong Mai Dinh, Quang-Huy Nguyen +2
Expensive multi-objective optimization problems (EMOPs) are common in real-world scenarios where evaluating objective functions is costly and involves extensive computations or phy…
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
Cuong Chi Le, Hoang-Chau Truong-Vinh, Huy Nhat Phan +3
Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for cod…
Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendations
Hai-Dang Kieu, Minh Duc Nguyen, Thanh-Son Nguyen +1
Recent advancements in Large Language Models (LLMs) have shown significant potential in enhancing recommender systems. However, addressing the cold-start recommendation problem, wh…