most citedAgent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

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…

cs.LG2026

SPARK: Learning from Verification in Speculative GRPO Rollouts

Nhat Minh Pham, Duy Tung Doan, Thi Duyen Ngo +3

Group Relative Policy Optimization (GRPO) has become a standard approach for improving the reasoning abilities of large language models, but its training is costly because each ste…