Package for working with hypernetworks in PyTorch.
-
Updated
Sep 7, 2023 - Python
Package for working with hypernetworks in PyTorch.
[WWW2023] PyTorch implementation of "DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization".
Hypernetwork training considerations and implementation types in PyTorch. Includes classification and time-series examples alongside 1D GroupConv Parallelization.
Code for ICLR 2022 Paper (HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning)
AAAI'26 Oral: "WeightFlow: Learning Stochastic Dynamics via Evolving Weight of Neural Network"
Hypernetwork-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels
Database for "HyperSOR: Context-aware graph hypernetwork for salient object ranking", TPAMI 2024
Official repo for the "HyDA: A Hypernetwork Framework for Unsupervised Domain Adaptation for Medical Images" MICCAI 2025 paper.
Imaging tools CLI for preprocessing datasets before model training.
Using teacher assistant networks to distill recommender systems
Hypergraph-based Investigation of Perturbation Effects and Resilience (HIPER) provides optimized data structures and algorithms for hypernetwork analysis and attack simulation.
Hypernetwork-driven LoRA distillation from Qwen3-Coder teacher trajectories
Instant Knowledge Internalization — Convert documents into LoRA adapter weights using Text-to-LoRA hypernetworks. No fine-tuning, no gradient descent — just inference.
Zero-shot semantic HyperLoRA generation on constrained SVD manifolds
3D Real Scene Style Transfer of Neural Radiance Fields with Hash Encoding and HyperNet
Generative Mixture-of-Experts: Synthesize 360M+ dense parameters on-the-fly from micro recipes (<2MB) in milliseconds
To associate your repository with the hypernetwork topic, visit your repo's landing page and select "manage topics."