Hypernetworks

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting
Oct 8, 2026Darahaas Nallagatla, Darryl Cherian Jacob, Pan HeTime Series Forecasting Time-Series Foundation Models
Auburn University
Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models
Oct 8, 2026Peter Devine, Nick Ryan, Benjamin Sirb +1Hypernetworks Parameter-Efficient Fine-Tuning
Interval
Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
Oct 1, 2026Azal Ahmad Khan, Keshav Ramji, Tahira Naseem +2Test-Time Adaptation Test-Time Scaling
University of Minnesota · IBM Research AI
CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations
Oct 1, 2026Adir Dayan, Yam Eitan, Haggai MaronModel Compression Hypernetworks
Technion – Israel Institute of Technology · NVIDIA Research
CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork
Oct 1, 2026Wojciech Gromski, Patryk Krukowski, Jan Miksa +2Subject-Driven Image Generation T2I Generation
Wrocław University of Science and Technology · IDEAS Research Institute · Jagiellonian University, Krak´ow +2
On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D
Sep 30, 2026Fabio J. Fehr, Philip TorrFew-Shot Learning Hypernetworks
University of Oxford
Transferable Graph Metanetworks
Sep 30, 2026Yuxin Ma, Adir Dayan, Yam Eitan +2Neural Network Generalization Hypernetworks
Department of Applied Mathematics and Statistics, Johns Hopkins University · Technion · NVIDIA
Doc2LoRA Provides Decodable Representations of Scientific Ideas
Sep 29, 2026Chand Sahil Mansuri, Joel Zachariah, Sadamori KojakuText Embeddings Low-Rank Adaptation
School of Systems Science and Industrial Engineering Binghamton University, Binghamton, NY, USA
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
Sep 21, 2026Sean Augenstein, Li Ding, Jihwan Lee +2On-Device Language Model Inference Low-Rank Adaptation
Google · Formerly at Google, work done while at Google
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks
Sep 17, 2026Cheng Jing, Abhishek Verma, Kallol Bera +2Amortized Inference Meta-Learning
Arizona State University · Applied Materials Inc.
Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
Sep 16, 2026Jinli Hu, Ross M. Clarke, Yichuan Zhang +1Continual Learning for LLMs Hypernetworks
Boltzbit Limited · University of Cambridge
Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations
Aug 31, 2026Shijun ZhangHypernetworks Neural Network Approximation Theory
Department of Applied Mathematics Hong Kong Polytechnic University
Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters
Jul 30, 2026Pankayaraj Pathmanathan, Furong HuangLLM Alignment LLM Safety Alignment
University of Maryland College Park
Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks
Jul 27, 2026Ricard Marsal I Castan, Aman Arora, Antoine Richard +3Robotic Control Hypernetworks
University of Luxembourg · 2Georgia Institute of Technology
HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems
Jul 21, 2026Nicolò Botteghi, Gabriele Pascali, Urban Fasel +1RL Control Hypernetworks
MOX, Department of Mathematics · Politecnico di Milano · Milano, Italy +3
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Jul 21, 2026Nischay Dhankhar, Dos Baha, Abulhair SaparovKnowledge Augmentation for Language Models Hypernetworks
Nace AI · Purdue University
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
Jul 8, 2026Tobias Göbel, Julian R. Ebelt, Zier Mensch +2Phase Transitions Neural Network Interpretability
Institute of Physics, University of Amsterdam, Amsterdam, Netherlands · Department of Physics, National Taiwan University, Taipei, Taiwan · Department of Physics, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA +2
Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
Jun 29, 2026Dongliang Cao, Florian BernardNon-Rigid Shape Correspondence Hypernetworks
University of Bonn, Germany
Neural Texture Compression using Hypernetworks
Jun 25, 2026Belcour LaurentLearned Image Compression Hypernetworks
Intel Corporation
Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation
Jun 11, 2026Xiaomeng Yang, Yanyu Li, Gordon Guocheng Qian +7Image-to-Video Generation Video Diffusion Models
1Northeastern University, 2Snap Inc.
Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models
Jun 4, 2026Sunny Gupta, Shambhavi Shanker, Amit SethiFederated Learning Aggregation Non-IID Federated Learning
Indian Institute of Technology, Bombay
Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data
May 29, 2026Haoan Feng, Xin Xu, Leila De FlorianiImplicit Neural Representations Geospatial Representation Learning
University of Maryland, College Park MD, USA
Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation
May 20, 2026Abhishek Dinkar Jagtap, Sanath Tiptur Sadashivaiah, Andreas FestagHypernetworks V2X Communication
CARISSMA Institute for Electric, COnnected, and Secure Mobility (C-ECOS), Technische Hochschule Ingolstadt, Ingolstadt, 85049, Germany. · University of Applied Sciences Aschaffenburg, Aschaffenburg, 63743, Germany.
DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation
May 20, 2026Hanxiang Ren, Pei Zhou, Xunzhe Zhou +1Language-Conditioned Robot Manipulation Visuomotor Policy Learning
‡Zhejiang University §The University of Hong Kong ¶TranscEngram
A Two-Phase Adaptive Balanced Penalty Method for Controllable Pareto Front Learning under Split Feasibility Conditions
May 19, 2026Nguyen Viet Hoang, Dung D. Le, Tran Ngoc ThangHypernetworks Multi-Objective Optimization
Hypernetworks for Dynamic Feature Selection
May 12, 2026Javier Fumanal-Idocin, Raquel Fernandez-Peralta, Javier Andreu-PerezHypernetworks Feature Selection
University of Essex Wivenhoe Park, Colchester, United Kingdom · Slovak Academy of Sciences Štefánikova 49, 814 73 Bratislava, Slovakia
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
May 11, 2026Yujia Cai, Boxuan Li, Chenghao Xu +1Multimodal IR VLM Adaptation
School of Computer Science and Technology, Xidian University, Xi’an, Shaanxi, China · School of Electronic Engineering, Xidian University, Xi’an, Shaanxi, China
HyperTransport: Amortized Conditioning of T2I Generative Models
May 7, 2026Valentino Maiorca, Eleonora Gualdoni, Xavier Suau +3T2I Generation Hypernetworks
1ISTA · 2Apple
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
May 7, 2026Haisen He, Xiangyu Zou, SongLin Dong +3Low-Rank Adaptation All-in-One Image Restoration
Southern University of Science and Technology · Shenzhen University · Shenzhen University of Advanced Technology +1
LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
May 7, 2026Niels Vyncke, Pooya Ashtari, Aleksandra PižuricaMissing-Modality Learning Cross-Modality Medical Image Segmentation
Department of Telecommunications and Information Processing Ghent University Ghent, Belgium

Oct 8, 2026, cs.LGJ/K move · Enter open · S save

AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting

Darahaas Nallagatla, Darryl Cherian Jacob, Pan He

Auburn University

Time Series Forecasting Time-Series Foundation Models Low-Rank Adaptation Hypernetworks Zero-Shot Time Series Forecasting

Open paper AskPDF arXiv

Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Existing all-in-one methods learn a single set of dataset-level parameter updates and apply the same adapted model to every input. As a result, they cannot adapt the model parameters to the temporal patterns, seasonality and dynamics of each input time series. This limits their ability to produce forecasts that are tailored to heterogeneous inputs. To address this limitation, we propose AdaCast, a conditional parameter generation framework for time-series forecasting. AdaCast uses a generator to produce input-specific low-rank parameter updates for a frozen pretrained TSFM. These updates adapt the model to each input during both training and inference. Across six public benchmarks, AdaCast consistently outperforms static adaptation baseline in in-domain forecasting and improves zero-shot generalization to held-out datasets across domains. These results demonstrate that conditional parameter generation provides an effective approach for adaptive forecasting.

Momentum

Related topics

Latest papers 34