43 citations · 101 across the 29 of their papers we have counts for
4 papers · 1 filter
Learning Generalizable Behaviors for Terminal Agents
Yihang Yao, Bo Pang, Xuan Phi Nguyen +3
Terminal agents are a compelling application of large language models (LLMs), with the potential to integrate deeply into users' daily workflows. Reinforcement learning (RL) is a k…
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
Xuan-Phi Nguyen, Shrey Pandit, Austin Xu +2
Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that ev…
Differentiable Window for Dynamic Local Attention
Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty +1
We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection. While universally applicable, we demonstrate a compelling use case…
Tree-structured Attention with Hierarchical Accumulation
Xuan-Phi Nguyen, Shafiq Joty, Steven C. H. Hoi +1
Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-…