8 papers
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…
SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts
Nhat Minh Pham, Duy Tung Doan, Thi Duyen Ngo +2
Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains a major efficiency bottleneck.…
CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation
Duy Tung Doan, Quang Huy Phung, Dzung Nguyen +1
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated executio…
KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
Chi Minh Bui, Ngoc Mai Thieu, Van Vinh Nguyen +2
The integration of knowledge graphs (KGs) with large language models (LLMs) offers significant potential to improve the retrieval phase of retrieval-augmented generation (RAG) syst…
Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
Quang-Vinh Nguyen, Quang-Chieu Nguyen, Hoang Pham +1
Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD syste…
Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
Hoang Pham, Thuy-Duong Nguyen, Khac-Hoai Nam Bui
This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agen…