Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver.
hub Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (62%).
43
Pith papers citing it
Background
62% of classified citations
abstract
This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the relationship between a genotype - the hypernetwork - and a phenotype - the main network. Though they are also reminiscent of HyperNEAT in evolution, our hypernetworks are trained end-to-end with backpropagation and thus are usually faster. The focus of this work is to make hypernetworks useful for deep convolutional networks and long recurrent networks, where hypernetworks can be viewed as relaxed form of weight-sharing across layers. Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks. Our results also show that hypernetworks applied to convolutional networks still achieve respectable results for image recognition tasks compared to state-of-the-art baseline models while requiring fewer learnable parameters.
hub tools
citation-role summary
background 8
method 5
citation-polarity summary
representative citing papers
OnlyDense learns neural basis functions to approximate particle system states in a low-dimensional linear Hilbert subspace, unifying projection-based ROM with deep learning for accurate SPH dynamics modeling with 32 bases at R²>0.99.
CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
A hypernetwork generates complete task-specific visuomotor policy parameters from instructions alone to structurally eliminate observation leakage in language-conditioned robotic control.
TFlow enables multi-agent LLMs to collaborate via transient low-rank LoRA perturbations derived from sender activations, yielding up to 8.5 accuracy gains and 83% token reduction versus text-based baselines on Qwen3-4B models.
A hypernetwork maps style motion embeddings to LoRA updates that stylize text-driven motion diffusion models with improved generalization to unseen styles via contrastive structuring of the style space.
Events trigger on-the-fly LoRA module generation via hypernetworks over a shared team policy in MARL, paired with a Neural Manifold Diversity metric, enabling sequential role reassignment while preserving reward maximization.
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
CLOVER augments value decomposition with a GNN mixer whose weights depend on the realized wireless communication graph, proving permutation invariance, monotonicity, and greater expressiveness than QMIX while showing gains on Predator-Prey and Lumberjacks under p-CSMA channels.
IA-VAE augments amortized variational inference with hypernetwork-generated instance-adaptive modulations, strictly containing the standard variational family and improving held-out ELBO on synthetic and image data.
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
ReWeaver reconstructs topology-accurate 3D garments and sewing patterns from sparse multi-view images by predicting seams and panels in 2D UV and 3D space using a new 100k-sample synthetic dataset.
UniReg introduces a conditional unified neural model for multi-scenario CT registration that conditions on anatomical priors, inter/intra-subject type, and instance features to achieve higher accuracy and cross-scenario generalization than task-specific networks.
Automated search discovers Swish activation f(x) = x * sigmoid(βx) that improves top-1 ImageNet accuracy over ReLU by 0.9% on Mobile NASNet-A and 0.6% on Inception-ResNet-v2.
DroneFINE is a domain-aware PEFT approach for VLM-based drone detectors using foreground-aware multi-path adaptation and text-conditioned background suppression, outperforming standard PEFT and matching full fine-tuning on VisDrone and UAVDT with fewer trainable parameters.
Prompt2Effect is a weight-driven hypernetwork that synthesizes LoRA adapters for I2V models from prompts and base weights via SVD parameterization, matching fine-tuned quality at 3.3s inference instead of 56 GPU hours.
Polaris retrieves and integrates relevant models from a large library of checkpoints and adapters to enable scalable instruction-guided image generation and editing without additional training.
Introduces a terrain-specific benchmark showing cross-domain gaps in INR methods and demonstrates that HUVR+SIREN achieves superior height and derivative fidelity in a compact quantized format.
InfoAtlas is a pretrained neural model for zero-shot mutual information estimation that matches state-of-the-art accuracy with 100x speedup and handles varying dimensions via a single model.
Hyper-V2X uses a Bayesian hypernetwork with partial weight generation and V2X context embedding to produce calibrated epistemic and aleatoric uncertainty estimates for multi-agent BEV segmentation on the OPV2V benchmark.
MULTI uses two-stage textual inversion to disentangle camera lens, sensor, view, and domain factors for novel image generation, supporting dataset extension and ControlNet modifications on the new DF-RICO benchmark.
Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
EnvCoLoc combines environment-conditioned diffusion meta-learning with 3D point cloud descriptors to reduce mean localization error by up to 20% in NLOS WiFi scenarios using only 10 support samples.
RareCP improves interval efficiency for time series conformal prediction by retrieving and weighting regime-specific calibration examples while adapting to drift and maintaining coverage.
citing papers explorer
-
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
-
Hyperfastrl: Hypernetwork-based reinforcement learning for unified control of parametric chaotic PDEs
Hypernetworks map a forcing parameter directly to policy weights in an RL framework, enabling unified stabilization of the Kuramoto-Sivashinsky equation across regimes with KAN architectures showing strongest extrapolation.
-
HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging
HyperFitS is a hypernetwork for configurable spectral fitting in 1H MRSI that matches conventional LCModel results while processing whole-brain data in seconds instead of hours and adapting to varied protocols without retraining.
-
Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
MaskGen improves domain generalization for biomedical image segmentation by using source intensities plus domain-stable foundation model representations with minimal added complexity.
-
Adaptive Learned State Estimation based on KalmanNet
AM-KNet adds sensor-specific modules, hypernetwork conditioning on target type and pose, and Joseph-form covariance estimation to KalmanNet, yielding better accuracy and stability than base KalmanNet on nuScenes and View-of-Delft data.