8 citations · 16 across the 13 of their papers we have counts for
7 papers · 2 filters
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Xujia Wang, Haiyan Zhao, Shuo Wang +2
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-ta…
LLMMapReduce: Simplified Long-Sequence Processing using Large Language Models
Zihan Zhou, Chong Li, Xinyi Chen +11
Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we prop…
DeepNote: Note-Centric Deep Retrieval-Augmented Generation
Ruobing Wang, Qingfei Zhao, Yukun Yan +9
Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for question-answering (QA) by incorporating external knowledge. Ho…
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Bowen Ping, Shuo Wang, Hanqing Wang +7
Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs beco…
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Zhiyu Yang, Zihan Zhou, Shuo Wang +10
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Des…
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Hanqing Wang, Bowen Ping, Shuo Wang +4
LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills.…
OneBit: Towards Extremely Low-bit Large Language Models
Yuzhuang Xu, Xu Han, Zonghan Yang +5
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computa…