Search Results - "Pu, George"

Seeing Through Walls: Real-Time Digital Twin Modeling of Indoor Spaces by Pu, George, Wei, Paul, Aribe, Amanda, Boultinghouse, James, Dinh, Nhi, Xu, Fang, Du, Jing

“…As the need for situational awareness rises in search and rescue tasks, systems for human spatial sensing augmentation in complex-built environments has become…”
Get full text

Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning by Zhou, Yanlin, Lu, Fan, Pu, George, Ma, Xiyao, Sun, Runhan, Chen, Hsi-Yuan, Li, Xiaolin

“…We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating…”
Get full text

Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs by Pu, George, Jain, Anirudh, Yin, Jihan, Kaplan, Russell

“…As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning…”
Get full text

Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs by Chan, Yung-Chieh, Pu, George, Shanker, Apaar, Suresh, Parth, Jenks, Penn, Heyer, John, Denton, Sam

“…As large language models (LLMs) are applied to more use cases, creating high quality, task-specific datasets for fine-tuning becomes a bottleneck for model…”
Get full text

"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters by Wan, Yixin, Pu, George, Sun, Jiao, Garimella, Aparna, Chang, Kai-Wei, Peng, Nanyun

“…Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content, including professional…”
Get full text

Server Averaging for Federated Learning by Pu, George, Zhou, Yanlin, Wu, Dapeng, Li, Xiaolin

“…Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server. The global…”
Get full text

Distilled One-Shot Federated Learning by Zhou, Yanlin, Pu, George, Ma, Xiyao, Li, Xiaolin, Wu, Dapeng

“…Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is…”
Get full text

Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning by Zhou, Yanlin, Lu, Fan, Pu, George, Ma, Xiyao, Sun, Runhan, Chen, Hsi-Yuan, Li, Xiaolin, Wu, Dapeng

“…IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019) We propose a deep reinforcement learning (DRL) methodology for the tracking,…”
Get full text