Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" (CVPR 2022) https://arxiv.org/abs/2111.15666

Hypernetworks that update LLMs to remember factual information

PyTorch implementation of HyperNetworks (Ha et al., ICLR 2017) for ResNet (Residual Networks)

Package for working with hypernetworks in PyTorch.

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

Easy Hypernetworks in Pytorch and Jax

A collection of weight space learning including papers, codes, and datasets.

The Official Implementation for "HAIR: Hypernetworks-based All-in-One Image Restoration".

A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems

This is the official implementation of "DHP: Differentiable Meta Pruning via HyperNetworks".

Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]

HyperPCM: Robust task-conditioned modeling of drug-target interactions

Dynamic weight generation for recursive transformers via input-conditioned LoRA modulation

The official implementation of the "HyperPocket: Generative Point Cloud Completion" paper in PyTorch

Code for Stochastic Hyperparameter Optimization through Hypernetworks

GPU-accelerated neural network operations using Vulkan compute shaders.

The official implementation of the "Hypernetwork approach to generating point clouds" paper

Official repository for "Estimating Epistemic and Aleatoric Uncertainty with a Single Model"

Neuromodulatory Control Networks (NCNs), a novel LLM architectural modification inspired by the neuromodulatory systems in the vertebrate brain.