5 papers
CarbonScaling: Extending Neural Scaling Laws for Carbon Footprint in Large Language Models
Lei Jiang, Fan Chen
Large language models (LLMs) increasingly follow neural scaling laws that tie performance gains to rapidly expanding computational budgets, raising concerns about the sustainabilit…
LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites
Lei Jiang, Adrian Ildefonso, Daniel Loveless +1
Large language models (LLMs) impose rapidly growing energy demands, creating an emerging energy and carbon crisis driven by large-scale inference. Solar-powered, AI-enabled low Ear…
Qracle: A Graph-Neural-Network-based Parameter Initializer for Variational Quantum Eigensolvers
Chi Zhang, Lei Jiang, Fan Chen
Variational Quantum Eigensolvers (VQEs) are a leading class of noisy intermediate-scale quantum (NISQ) algorithms with broad applications in quantum physics and quantum chemistry.…
QSeer: A Quantum-Inspired Graph Neural Network for Parameter Initialization in Quantum Approximate Optimization Algorithm Circuits
Lei Jiang, Chi Zhang, Fan Chen
To mitigate the barren plateau problem, effective parameter initialization is crucial for optimizing the Quantum Approximate Optimization Algorithm (QAOA) in the near-term Noisy In…
IoTCO2: Assessing the End-To-End Carbon Footprint of Internet-of-Things-Enabled Deep Learning
Fan Chen, Shahzeen Attari, Gayle Buck +1
To improve privacy and ensure quality-of-service (QoS), deep learning (DL) models are increasingly deployed on Internet of Things (IoT) devices for data processing, significantly i…