Efficient-Multimodal-LLMs-Survey and Efficient-LLMs-Survey
These two surveys are **complementary**, with the first focusing specifically on multimodality within efficient LLMs and the second providing a broader overview of efficiency techniques applicable across all LLMs, allowing researchers to use both to gain a comprehensive understanding of the field.
About Efficient-Multimodal-LLMs-Survey
swordlidev/Efficient-Multimodal-LLMs-Survey
Efficient Multimodal Large Language Models: A Survey
This is a survey for researchers and engineers working with multimodal large language models (MLLMs). It provides a comprehensive overview of efficient MLLMs, outlining their architectures, strategies for efficiency, and real-world applications. The resource takes in the latest research papers and categorizes them, allowing practitioners to understand the current landscape, limitations, and future directions of MLLM development, particularly for resource-constrained environments.
About Efficient-LLMs-Survey
AIoT-MLSys-Lab/Efficient-LLMs-Survey
[TMLR 2024] Efficient Large Language Models: A Survey
This survey paper helps researchers and practitioners navigate the rapidly evolving landscape of Large Language Models (LLMs) by offering a structured overview of techniques designed to improve their efficiency. It takes in existing research papers on LLM optimization and organizes them into a clear taxonomy, outputting a systematic understanding of different approaches. This resource is intended for AI researchers, machine learning engineers, and data scientists who are working with LLMs and need to make them more performant or cost-effective.
Scores updated daily from GitHub, PyPI, and npm data. How scores work