alecwangcq
Reinforcement learning ∩ LLMs, Generative models, Artificial intelligence
San Francisco, CA
Pinned Repositories
coco-caption-python3
Conv_LSTM
EigenDamage-Pytorch
Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934
f-divergence-dpo
Direct preference optimization with f-divergences.
GraSP
Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH
KFAC-Pytorch
Pytorch implementation of KFAC and E-KFAC (Natural Gradient).
Prototypical-network
show-attend-and-tell
Weight-Decay
Regularization, Neural Network Training Dynamics
Neural-Kernel-Network
Code for "Differentiable Compositional Kernel Learning for Gaussian Processes" https://arxiv.org/abs/1806.04326
alecwangcq's Repositories
alecwangcq/KFAC-Pytorch
Pytorch implementation of KFAC and E-KFAC (Natural Gradient).
alecwangcq/EigenDamage-Pytorch
Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934
alecwangcq/GraSP
Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH
alecwangcq/show-attend-and-tell
alecwangcq/f-divergence-dpo
Direct preference optimization with f-divergences.
alecwangcq/Conv_LSTM
alecwangcq/coco-caption-python3
alecwangcq/Prototypical-network