LLM RBMT

LLM-based Robotic Machine Translation (RBMT) research explores leveraging the power of large language models (LLMs) to improve and expand machine translation capabilities, particularly for low-resource or endangered languages. Current efforts focus on enhancing LLM efficiency through techniques like query-aware inference acceleration and token compression, as well as developing novel architectures such as multi-expert LLMs and integrating LLMs with rule-based systems or behavior trees for more robust and adaptable performance. This work holds significant potential for advancing both natural language processing and robotics, enabling more accurate and efficient translation, improved robotic task execution, and facilitating language preservation efforts.

Papers

November 8, 2024

LLM-PySC2: Starcraft II learning environment for Large Language Models
Zongyuan Li, Yanan Ni, Runnan Qi, Lumin Jiang, Chang Lu, Xiaojie Xu, Xiangbei Liu, Pengfei Li, Yunzheng Guo, Zhe Ma, Xian Guo, Kuihua Huang, Xuebo Zhang
Multi Agent Challenge StarCraft II LLM RBMT

October 14, 2024

NT-LLM: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models
Yanbiao Ji, Chang Liu, Xin Chen, Yue Ding, Dan Luo, Mei Li, Wenqing Lin, Hongtao Lu
Graph Neural Network Graph Learning Graph Level Task Text to Graph LLM RBMT Graph Integration

July 3, 2024

LLMcap: Large Language Model for Unsupervised PCAP Failure Detection
Lukasz Tulczyjew, Kinan Jarrah, Charles Abondo, Dina Bennett, Nathanael Weill
Large Language Model Self Supervised Learning Error Detection Deep Packet Inspection LLM RBMT

June 11, 2024

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models
Jingyao Li, Han Shi, Xin Jiang, Zhenguo Li, Hong Xu, Jiaya Jia
LLM RBMT Needle in a Haystack

May 14, 2024

LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages
Jared Coleman, Bhaskar Krishnamachari, Khalil Iskarous, Ruben Rosales
Machine Translation Low Resource Low Priority LLM Based Machine Translation LLM RBMT

April 11, 2024

A Multi-Expert Large Language Model Architecture for Verilog Code Generation
Bardia Nadimi, Hao Zheng
Verilog Code Generation Functional Verilog Description LLM RBMT Expert Language Model Design Knowledge

April 8, 2024

LLM-BT: Performing Robotic Adaptive Tasks based on Large Language Models and Behavior Trees
Haotian Zhou, Yunhan Lin, Longwu Yan, Jihong Zhu, Huasong Min
Behavior Tree Task Adaptation Bidirectional Encoder Representation Complex Robotic Task LLM RBMT Adaptive Robotics

March 2, 2024

LLMCRIT: Teaching Large Language Models to Use Criteria
Weizhe Yuan, Pengfei Liu, Matthias Gallé
Large Language Model Task Completion Feedback Generation Context Demonstration Likely Criterion LLM RBMT

October 24, 2023

TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction
Junyi Liu, Liangzhi Li, Tong Xiang, Bowen Wang, Yiming Qian
Large Language Model Retrieval Augmentation Inference Cost Commercial Large Language Model Semantic Compression Token Compression LLM RBMT

September 29, 2023

PB-LLM: Partially Binarized Large Language Models
Yuzhang Shang, Zhihang Yuan, Qiang Wu, Zhen Dong
Large Language Model Neural Network Post Training Quantization Binarization Method Low Bit Quantization LLM RBMT Partial Binarization

May 29, 2023

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, Vikas Chandra
Large Language Model Training Free Quantization Aware Training Quantization Level Free Distillation LLM RBMT

May 23, 2023

RET-LLM: Towards a General Read-Write Memory for Large Language Models
Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze
Large Language Model Natural Language Processing Temporal Question LLM RBMT