Overview

Hypernetwork research studies how one neural network can produce another model’s weights or weight updates, allowing a model to adapt without training a separate set of parameters for every task. Common approaches generate low-rank adapters such as LoRA, use latent or coordinate-based weight generators, or condition generation on task descriptions, examples, or input features. These methods are used for efficient personalization, continual learning, model compression, uncertainty estimation, and adaptation across domains such as language, vision, control, and scientific computing. A central challenge is making generated weights reliable on unseen tasks and architectures while balancing adaptation quality, inference cost, and retention of previously learned capabilities.

Latest papers

CardsList

67 papers5 papers in the last four weeks, down 72% on the four weeks before. 0.0% of all new papers.

  1. MI-Hyper: Generating Multiple Instance Models for Weight Space Transfer Learning in Histopathology via Mixed Tasks Pretrained HyperNetwork

    Nov 17, 2026Xitong Ling, Yousef Kotp, Weiming Chen +9Whole-Slide Image AnalysisWeight-Space Learning

  2. Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations

    Nov 7, 2026Lulu Cai, Hanxiang Ren, Siyan Dong +5HypernetworksImplicit Neural Representations

  3. SKILL2STEER: One-Pass Hypernetwork for Mapping Natural-Language Skills to Low-Rank Post-Block Activation Shifts

    Nov 3, 2026Ran Li, Lei ChenLLM Agent Skill LearningActivation Steering

  4. HyperRepair: Recovering Forgotten General Capabilities of Fine-Tuned Language Models

    Oct 30, 2026Junrong Tang, Jianghui Wang, Hao Kong +2Fine-Tuning Language ModelsCatastrophic Forgetting

  5. In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models

    Oct 25, 2026Yiwei Guo, Siqi Huang, Bohan Li +4Compositional GeneralizationAudio-Language Models

  6. Bifurcations from Weight Space: JEPAWG on Parametric Dynamical Systems

    Oct 22, 2026Tobias Göbel, Miranda C. N. ChengWeight-Space AnalysisHypernetworks

  7. ReVision: Reprogramming Image Generators for Dense Visual Perception

    Oct 16, 2026Yitong Yang, Yinglin Wang, Xuexin Liu +6Multi-Task LearningHypernetworks

  8. Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks

    Oct 15, 2026Md Farhan Ishmam, Minh Pham Dinh, Kenneth MarinoWeb AgentsHypernetworks

  9. Graph Metanetworks for Transformer Based Language Models

    Oct 13, 2026Yonathan Wolanowsky, Guy Bar-Shalom, Fabrizio Frasca +1Weight-Space LearningTransformer

  10. Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer

    Oct 2, 2026Leonard Popp, Danni Liu, Supriti Sinhamahapatra +1Text Style TransferText Generation

  11. HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

    Oct 2, 2026Donggyun Kim, Jack Lu, Chanwoo Kim +2Efficient Language Model ReasoningLLM Inference Acceleration

  12. Learning to Predict Distributions over Weight Updates for Test-Time Adaptation

    Oct 1, 2026Azal Ahmad Khan, Keshav Ramji, Tahira Naseem +2Test-Time AdaptationTest-Time Scaling

  13. CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations

    Oct 1, 2026Adir Dayan, Yam Eitan, Haggai MaronModel CompressionHypernetworks

  14. CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork

    Oct 1, 2026Wojciech Gromski, Patryk Krukowski, Jan Miksa +2Subject-Driven Image GenerationT2I Generation

  15. Transferable Graph Metanetworks

    Sep 30, 2026Yuxin Ma, Adir Dayan, Yam Eitan +2Neural Network GeneralizationHypernetworks

  16. Doc2LoRA Provides Decodable Representations of Scientific Ideas

    Sep 29, 2026Chand Sahil Mansuri, Joel Zachariah, Sadamori KojakuText EmbeddingsLow-Rank Adaptation

  17. HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models

    Sep 25, 2026Yi Sun, Xinhao Zhong, Zhiqi Zhang +3Safe T2I GenerationDiffusion Model Unlearning

  18. Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks

    Sep 24, 2026Phillip Lo, Sudarshan Babu, Dari Kimanius +13D Representation LearningCryo-Electron Microscopy

  19. LoRA-generating hypernetworks for efficient on-device LLM generative personalization

    Sep 21, 2026Sean Augenstein, Li Ding, Jihwan Lee +2On-Device Language Model InferenceLow-Rank Adaptation

  20. Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks

    Sep 17, 2026Cheng Jing, Abhishek Verma, Kallol Bera +2Amortized InferenceMeta-Learning

  21. Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data

    Sep 16, 2026Jinli Hu, Ross M. Clarke, Yichuan Zhang +1Continual Learning for LLMsHypernetworks

  22. One Evaluation, Any Operating Point: Hypernetwork-Amortized MeanFlow for 3D MRI Reconstruction

    Sep 15, 2026Ruibo WangAccelerated MRI ReconstructionMagnetic Resonance Imaging

  23. Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations

    Aug 31, 2026Shijun ZhangHypernetworksNeural Network Approximation Theory

  24. Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates

    Aug 27, 2026Romain Claret, Michael O'Neill, Paul Cotofrei +1NeuroevolutionHypernetworks