Biography
Zeyu Yang is a DPhil student at Oxford e-Research Centre, supervised by Prof Wes Armour and Dr Karel Adamek. Previously he completed his MEng in Electrical and Electronic Engineering at Imperial College London.
Most Recent Publications
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Part-time power measurements: nvidia-smi's lack of attention
Part-time power measurements: nvidia-smi's lack of attention
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training
Research Interests
- Computer Architecture
- Machine Learning
- Reconfigurable Computing
- Heterogeneous Computing
- Robotics
Research Groups
Related Academics
Most Recent Publications
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Part-time power measurements: nvidia-smi's lack of attention
Part-time power measurements: nvidia-smi's lack of attention
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training
Most Recent Publications
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy
Part-time power measurements: nvidia-smi's lack of attention
Part-time power measurements: nvidia-smi's lack of attention
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Towards Instant Calibration in Myoelectric Prosthetic Hands: A Highly Data-Efficient Controller Based on the Wasserstein Distance
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training
Instinctive Real-time sEMG-based Control of Prosthetic Hand with Reduced Data Acquisition and Embedded Deep Learning Training