unites-lab Goto Github PK

lingual-smoe

[ICLR 2024] Code for the paper "Sparse MoE with Language-Guided Routing for Multilingual Machine Translation"

llm_toolbox

mc-smoe

[ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"

mew

[ECCV 2024] Code for the paper "Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network"

moe-quantization

Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"

moe-rbench

[ICML 2024] Code for the paper "MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts"

q-newton

Official code for the paper "Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent"

vpns

Codes for "Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective"