Weight-Space Learning

Latest papers

17 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures
Oct 15, 2026Michał Kozyra, Michael BronsteinWeight-Space Learning Weight-Space Analysis
University of Oxford · AITHYRA
Graph Metanetworks for Transformer Based Language Models
Oct 13, 2026Yonathan Wolanowsky, Guy Bar-Shalom, Fabrizio Frasca +1Weight-Space Learning Transformer
Technion – Israel Institute of Technology · NVIDIA Research
Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning
Sep 27, 2026Soutrik Sarangi, Yonatan Sverdlov, Adir Dayan +2Hidden-State Probing Weight-Space Learning
Microsoft · Faculty of Mathematics, Technion – Israel Institute of Technology · Faculty of Electrical and Computer Engineering, Technion – Israel Institute of Technology +1
Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification
Jul 31, 2026Stanislaw Janik, Michal ByraImplicit Neural Representations Neural Network Interpretability
Institute of Fundamental Technological Research, Polish Academy of Sciences, Warsaw, Poland · Samsung AI Center, Warsaw, Poland
Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
Jul 10, 2026Ethan SmithNeural Network Optimization Weight-Space Learning
Canva Research
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
Jul 3, 2026Aron Asefaw, Konstantinos Tzevelekakis, Damian Falk +2Cross-Modal Representation Learning Weight-Space Learning
School of Computer Science, University of St.Gallen, Switzerland.
Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space
Jul 2, 2026Di Wu, Huan Liu, Zhixiang Chi +3Temporal GNNs Implicit Neural Representations
University of Toronto · National University of Singapore · McMaster University +1
Weight-Space Geometry of Offline Reasoning Training
Jun 21, 2026Aleksandr Nikolich, Igor Kiselev, Vladimir Platonov +1RL for Language Models Direct Preference Optimization
1Keenable AI · 2Accenture · 3Yandex
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
May 22, 2026Eunwoo Heo, Kyeongkook Seo, Jaejun YooMulti-View Learning Weight-Space Analysis
Graduate School of Artificial Intelligence, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
Position: Weight Space Should Be a First-Class Generative AI Modality
May 18, 2026Zhangyang Wang, Peihao Wang, Kai WangGenerative Modeling Weight-Space Learning
University of Texas at Austin · Tencent
Quasi-Equivariant Metanetworks
Apr 26, 2026Viet-Hoang Tran, An Nguyen, Benoît Guérand +2Equivariant Neural Networks Weight-Space Learning
Department of Mathematics National University of Singapore
GeoSANE: Learning Geospatial Representations from Models, Not Data
Mar 24, 2026Joelle Hanna, Damian Falk, Stella X. Yu +1Weight-Space Learning Geospatial Representation Learning
University of St.Gallen · University of Michigan and UC Berkeley · ESA Φ-Lab
W2T: LoRA Weights Already Know What They Can Do
Mar 16, 2026Xiaolong Han, Ferrante Neri, Zijian Jiang +4Weight-Space Learning Low-Rank Adaptation
University of Surrey · Stanford University · University of Notre Dame
A Survey of Weight Space Learning: Understanding, Representation, and Generation
Mar 10, 2026Xiaolong Han, Zehong Wang, Bo Zhao +8Weight-Space Learning Weight-Space Analysis
University of Surrey · University of Notre Dame · University of California San Diego +4
Mapping Networks
Feb 22, 2026Lord Sen, Shyamapada MukherjeeWeight-Space Learning Neural Network Compression
National Institute of Technology Rourkela, Odisha, India
A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks
Feb 18, 2026Guy Bar-Shalom, Ami Tavory, Itay Evron +3Weight-Space Learning Kolmogorov-Arnold Networks
Technion, Meta · Meta · Meta, Ben-Gurion University of the Negev +1
Weight Space Representation Learning via Neural Field Adaptation
Dec 1, 2025Zhuoqian Yang, Mathieu Salzmann, Sabine SüsstrunkImplicit Neural Representations Low-Rank Adaptation
EPFL

Oct 15, 2026J/K move · Enter open · S save

Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures

Michał Kozyra, Michael Bronstein

University of Oxford · AITHYRA

Weight-Space Learning Weight-Space Analysis Equivariant Neural Networks Permutation-Equivariant Neural Networks Graph Representation Learning

Open paper AskPDF arXiv

Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require architecture-specific symmetry specifications, while neuron graphs make global attention costly. We introduce a typed graph organized around shared coordinate-permutation actions. Its nodes, called interfaces, represent coordinate spaces whose bound tensor axes must be permuted jointly; operation occurrences, called modules, form typed hyperedges. A compiler derives this graph from supported PyTorch models, with exact recovery of the permutation factors defined by its constraints. The Universal Weight Encoder (UWE) combines local equivariant updates to parameter features with global attention over invariant interface summaries. The small number of interfaces makes global attention practical, and a single encoder processes different supported architectures. UWE is competitive with architecture-specific state-of-the-art methods on established benchmarks. On a new zoo of 1,200 transformers spanning 100 architectures, it outperforms the evaluated baselines at ranking networks within unseen architectures, including architectures larger than those used for training, while using substantially less memory.