LLM Based
Large language model (LLM)-based systems are rapidly advancing, aiming to improve efficiency and accuracy across diverse applications. Current research focuses on optimizing LLM performance through techniques like multi-agent systems, adaptive reward model selection (e.g., using multi-armed bandits), and integrating LLMs with symbolic methods for enhanced reasoning and planning capabilities. This work is significant because it addresses limitations of existing LLMs, such as inconsistency, hallucination, and computational cost, leading to more robust and reliable AI systems for various domains including healthcare, robotics, and software engineering.
Papers
Can Language Models Use Forecasting Strategies?
Sarah Pratt, Seth Blumberg, Pietro Kreitlon Carolino, Meredith Ringel Morris
RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation
Jiaming Liu, Mengzhen Liu, Zhenyu Wang, Lily Lee, Kaichen Zhou, Pengju An, Senqiao Yang, Renrui Zhang, Yandong Guo, Shanghang Zhang
LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification
Chun Liu, Hongguang Zhang, Kainan Zhao, Xinghai Ju, Lin Yang
Deployment of Large Language Models to Control Mobile Robots at the Edge
Pascal Sikorski, Leendert Schrader, Kaleb Yu, Lucy Billadeau, Jinka Meenakshi, Naveena Mutharasan, Flavio Esposito, Hadi AliAkbarpour, Madi Babaiasl
Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation
Jiaming Liu, Chenxuan Li, Guanqun Wang, Lily Lee, Kaichen Zhou, Sixiang Chen, Chuyan Xiong, Jiaxin Ge, Renrui Zhang, Shanghang Zhang
Exploring the LLM Journey from Cognition to Expression with Linear Representations
Yuzi Yan, Jialian Li, Yipin Zhang, Dong Yan