1 citations · 2 across the 6 of their papers we have counts for
7 papers
GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
Boxiao Du, Boning Huangfu, Yizhou Luo +5
Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferen…
From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
Suqing Wang, Zuchao Li, Luohe Shi +4
Large language models (LLMs) have achieved remarkable success across various domains, driving significant technological advancements and innovations. Despite the rapid growth in mo…
Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models
Zihong Zhang, Liqi He, Zuchao Li +3
Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of "comprehend first, segment later", we propose a new framework to explore the…
Faster MoE LLM Inference for Extremely Large Models
Haoqi Yang, Luohe Shi, Qiwei Li +5
Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE mode…
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
Juncheng Yang, Zuchao Li, Shuai Xie +3
The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the perfor…
Multi-modal Auto-regressive Modeling via Visual Words
Tianshuo Peng, Zuchao Li, Lefei Zhang +3
Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning…
Sparse is Enough in Fine-tuning Pre-trained Large Language Models
Weixi Song, Zuchao Li, Lefei Zhang +2
With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient F…