Weight-Space Learning

Follow this topic Ask about this topic

Latest papers

26 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

TensorMutation: Learning Weight-Space Mutations of Deep Learning Models on Neural Graphs
Nov 6, 2026Zaheed Ahmed, Philip Makedonski, Jens GrabowskiMutation Testing DNN Testing
Institute of Computer Science, University of Göttingen, Germany
Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations
Nov 6, 2026Junru Hu, Cheng Tang, Wei Li +5Weight-Space Learning Weight-Space Analysis
Shanghai Artificial Intelligence Laboratory · Tongji University · Fudan University
Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games
Nov 6, 2026Eduardo C. Garrido-MerchánWeight-Space Learning Zero-Shot Learning
Universidad Pontificia Comillas (IIT, DIGNUM) Madrid, Spain
BUMP: Brief Unexpected Mid-Interpolation Peak
Nov 5, 2026Melinda Flóra Kiss, Márton Muntag, Adrián Csiszárik +1Weight-Space Learning Ensemble Learning
HUN-REN Alfréd Rényi Institute of Mathematics, Budapest, Hungary · Department of Computer Science, Eötvös Loránd University, Budapest, Hungary
Adapters as Data: The Latent Space of LoRAs
Nov 5, 2026Moritz Grävinghoff, Konstantin Wehmeyer, Aron Asefaw +2Low-Rank Adaptation Autoencoders
University of St.Gallen · Université de Montréal · Weight Space Labs
WeightLoop: Weight-Space Programming with Experimental Feedback
Nov 5, 2026Mengran Li, Bo Li, Weijing Zhao +6Language Model Self-Improvement Weight-Space Learning
Hong Kong Institute of Science and Innovation · University of Macau · Sichuan University +3
A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
Nov 4, 2026Scott Biggs, Bedionita Soro, Saumya Gupta +2Weight-Space Learning Language Model Pretraining
Khoury College of Computer Science, Northeastern University, Silicon Valley · MLAI Lab, KAIST · Khoury College of Computer Science, Northeastern University, Boston +2
Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection
Oct 24, 2026Akito Shinohara, Hiroaki AizawaOOD Detection Weight-Space Learning
Graduate School of Advanced Science and Engineering, Hiroshima University, Japan
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
Weight Space Learning for Certifiable Few-shot Transfer Learning
Feb 10, 2025Fady Rezk, Royson Lee, Henry Gouk +2Transfer Learning Weight-Space Learning
School of Informatics, University of Edinburgh · Samsung AI Center, Cambridge

Nov 6, 2026J/K move · Enter open · S save

TensorMutation: Learning Weight-Space Mutations of Deep Learning Models on Neural Graphs

Zaheed Ahmed, Philip Makedonski, Jens Grabowski

Institute of Computer Science, University of Göttingen, Germany

Mutation Testing DNN Testing Weight-Space Learning

Open paper AskPDF arXiv

Mutation testing for deep learning (DL) faces a cost-realism trade-off. The pre-training approach produces realistic but computationally expensive mutants, whereas existing post-training operators modify trained models efficiently but produce mutants that less closely resemble real faults. This study asks whether the trade-off is necessary: can the weight-space effect of a fault-informed pre-training mutation operator be predicted from a trained model, without retraining it? We answer this question with TensorMutation, which represents a trained model as a neural graph and uses a mutation-conditioned graph neural network (GNN) to predict parameter changes. The GNN is trained offline and reused across unseen models so that TensorMutation can generate executable mutants without retraining. We construct a corpus of 25,252 original-mutant pairs from 71 multilayer perceptron (MLP) classifiers using 11 fault-informed pre-training operators, including 25 newly curated subjects. TensorMutation partially reproduces the behavioral effects of pre-training mutations on nine held-out subjects, and direct weight-space supervision significantly improves weight-space fidelity. On 12 real-fault subjects, TensorMutation achieves the highest median behavioral similarity among the evaluated approaches. The improvement over the post-training tool DeepMutation++ is statistically significant (Holm-adjusted p=0.018), whereas the differences from the pre-training tool DeepCrime and the norm-matched random control are not significant. These results show that fault-informed pre-training mutations leave learnable structure in weight space that transfers to unseen models.