No article text was recorded for this version.
parameter generation scalability
Version 2 of 2106 papers117 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
- Blog: Model Lakes
- Blog: OCD: Learning to Overfit with Conditional Diffusion Models
- Blog: DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
- Blog: Efficient Training with Denoised Neural Weights
- Blog: Scaling Up Parameter Generation: A Recurrent Diffusion Approach
- Blog: Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions
- Blog: Conditional LoRA Parameter Generation
- Blog: Neural Network Diffusion
- Blog: Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
- Blog: Meta-Learning via Classifier(-free) Guidance
- Blog: We Should Chart an Atlas of All the World's Models
- Blog: Learning to Grow Pretrained Models for Efficient Transformer Training
- Blog: Riemannian Laplace approximations for Bayesian neural networks
- Blog: Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
- Blog: On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
- Blog: Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
- Blog: Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction
- Blog: Improving Hyperparameter Optimization with Checkpointed Model Weights
- Blog: Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
- Blog: Zero-Shot Forecasting of Network Dynamics through Weight Flow Matching
- Blog: HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
- Blog: pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning
- Blog: Model Zoo Dataset Samples for Scalable Weight Space Learning
- Blog: HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
- Blog: Towards Scalable and Versatile Weight Space Learning
- Blog: Learning to Rewind via Iterative Prediction of Past Weights for Practical Unlearning
- Blog: Bayesian Meta Sampling for Fast Uncertainty Adaptation
- Blog: VaiBot: Shuttle Between the Instructions and Parameters of Large Language Models
- Blog: Adaptivity and Modularity for Efficient Generalization Over Task Complexity
- Blog: PRANC: Pseudo RAndom Networks for Compacting deep models
- Blog: Set-based Neural Network Encoding
- Blog: Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices
- Blog: Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
- Blog: XOR-CD: Linearly Convergent Constrained Structure Generation
- Blog: MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities
- Blog: Towards Scalable and Versatile Weight Space Learning
- Blog: Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles
- Blog: Explaining neural networks without access to training data
- Blog: Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
- Blog: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction
- Blog: Variational Hyper-Encoding Networks
- Blog: Learning to Collaborate in Decentralized Learning of Personalized Models
- Blog: Weight Distillation: Transferring the Knowledge in Neural Network Parameters
- Blog: Learning the Space of Deep Models
- Blog: Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
- Blog: Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
- Blog: Learning to Refit for Convex Learning Problems
- Blog: LS-Merge: Merging Language Models in Latent Space
- Blog: Permutation Equivariant Neural Functionals
- Blog: ModelPred: A Framework for Predicting Trained Model from Training Data
- Blog: ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
- Blog: Weight Space Representation Learning via Neural Field Adaptation
- Blog: Meta-Learning via Classifier(-free) Diffusion Guidance
- Blog: Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning
- Blog: Generative Modeling of Weights: Generalization or Memorization?
- Blog: On the Internal Representations of Graph Metanetworks
- Blog: HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
- Blog: Family Discovery
- Blog: Instruction-Guided Autoregressive Neural Network Parameter Generation
Showing 60 of 106 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_generation_scalability_f18d5eec,
title = {parameter generation scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-generation-scalability/rdr_f18d5eeca08d4f34b0a9b54fc34c6948},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_parameter_generation_scalability_f18d5eec_v2,
title = {parameter generation scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-generation-scalability/rdr_f18d5eeca08d4f34b0a9b54fc34c6948/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}