Picture for Royson Lee

Royson Lee

A Bayesian Approach to Data Point Selection

Add code
Nov 06, 2024
Viaarxiv icon

Photon: Federated LLM Pre-Training

Add code
Nov 05, 2024
Figure 1 for Photon: Federated LLM Pre-Training
Figure 2 for Photon: Federated LLM Pre-Training
Figure 3 for Photon: Federated LLM Pre-Training
Figure 4 for Photon: Federated LLM Pre-Training
Viaarxiv icon

Progressive Mixed-Precision Decoding for Efficient LLM Inference

Add code
Oct 17, 2024
Figure 1 for Progressive Mixed-Precision Decoding for Efficient LLM Inference
Figure 2 for Progressive Mixed-Precision Decoding for Efficient LLM Inference
Figure 3 for Progressive Mixed-Precision Decoding for Efficient LLM Inference
Figure 4 for Progressive Mixed-Precision Decoding for Efficient LLM Inference
Viaarxiv icon

MobileQuant: Mobile-friendly Quantization for On-device Language Models

Add code
Aug 25, 2024
Figure 1 for MobileQuant: Mobile-friendly Quantization for On-device Language Models
Figure 2 for MobileQuant: Mobile-friendly Quantization for On-device Language Models
Figure 3 for MobileQuant: Mobile-friendly Quantization for On-device Language Models
Figure 4 for MobileQuant: Mobile-friendly Quantization for On-device Language Models
Viaarxiv icon

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Add code
May 23, 2024
Viaarxiv icon

How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor

Add code
Nov 30, 2023
Viaarxiv icon

FedL2P: Federated Learning to Personalize

Add code
Oct 03, 2023
Viaarxiv icon

NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution

Add code
Dec 15, 2022
Viaarxiv icon

Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation

Add code
Dec 15, 2022
Figure 1 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 2 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 3 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 4 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Viaarxiv icon

Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design

Add code
Sep 20, 2022
Figure 1 for Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
Figure 2 for Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
Figure 3 for Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
Figure 4 for Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
Viaarxiv icon