Workshop on Neural Network Weights as a New Data Modality

Accepted papers (45)

Fetched from OpenReview (v2) on 2026-06-10.

1. ☆A Model Zoo of Vision Transformers

   Damian Falk, Léo Meynent, Florence Pfammatter, Konstantin Schürholt, Damian Borth

2. ☆A Model Zoo on Phase Transitions in Neural Networks

   Konstantin Schürholt, Léo Meynent, Yefan Zhou, Yaoqing Yang, Damian Borth

3. ☆A Single Global Merging Suffices: Recovering Centralized Learning Performance in Decentralized Learning

   Tongtian Zhu, Tianyu Zhang, Mingze Wang, Zhanpeng Zhou, Can Wang

4. ☆Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space

   Vinicius Hernandes, Thomas Spriggs, Saqar Khaleefah, Eliska Greplova

5. ☆Adversarial Robustness in Parameter-Space Classifiers

   Tamir Shor, Ethan Fetaya, Chaim Baskin, Alex M. Bronstein

6. ☆ARC: Anchored Representation Clouds for High-Resolution INR Classification

   Joost Luijmes, Alexander Gielisse, Roman Knyazhitskiy, Jan van Gemert

7. ☆Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights

   Jonathan Kahana, Or Nathan, Eliahu Horwitz, Yedid Hoshen

8. ☆Can We Optimize Deep RL Policy Weights as Trajectory Modeling?

   Hongyao Tang

9. ☆Collaborative Time Series Imputation through Meta-learned Implicit Neural Representations

   Tong Nie, Wei Ma

10. ☆Compressive Meta-Learning

    Daniel Mas Montserrat, David Bonet, Maria Perera, Xavier Giró-i-Nieto, Alexander G. Ioannidis

11. ☆Cost-Efficient Continual Learning with Sufficient Exemplar Memory

    Dong Kyu Cho, Taesup Moon, Rumi Chunara, Kyunghyun Cho, Sungmin Cha

12. ☆Dataset Size Recovery from Fine-Tuned Model Weights

    Mohammad Salama, Jonathan Kahana, Eliahu Horwitz, Yedid Hoshen

13. ☆End-to-End Synthesis of Neural Programs in Weight Space

    Wenhao Li, Yudong Xu, Elias Boutros Khalil, Scott Sanner

14. ☆Equivariant Neural Functional Networks for Transformers

    Hoang V. Tran, Thieu Vo, An Nguyen The, Tho Tran Huu, Minh-Khoi Nguyen-Nhat, Thanh Tran, Duy-Tung Pham, Tan Minh Nguyen

15. ☆Finding Stable Subnetworks at Initialization with Dataset Distillation

    Luke McDermott, Rahul Parhi

16. ☆Flow to Learn: Flow Matching on Neural Network Parameters

    Daniel Saragih, Deyu Cao, Tejas Balaji, Ashwin Santhosh

17. ☆Fusion of Graph Neural Networks via Optimal Transport

    Weronika Ormaniec, Michael Vollenweider, Elisa Hoskovec

18. ☆GNNMERGE: MERGING OF GNN MODELS WITHOUT ACCESSING TRAINING DATA

    Vipul Garg, Ishita Thakre, Sayan Ranu

19. ☆GradMetaNet: An Equivariant Architecture for Learning on Gradients

    Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo Putterman, Haggai Maron

20. ☆Hyper-Align: Efficient Modality Alignment via Hypernetworks

    Jaisidh Singh, Diganta Misra, Boris Knyazev, Antonio Orvieto

21. ☆Improving Learning to Optimize Using Parameter Symmetries

    Guy Zamir, Aryan Dokania, Bo Zhao, Rose Yu

22. ☆Instruction-Guided Autoregressive Neural Network Parameter Generation

    Bedionita Soro, Bruno Andreis, Song Chong, Sung Ju Hwang

23. ☆Integrating Meta-Trained Hypernetworks with GBDTs and Retrieval for Tabular Data

    David Bonet, Marçal Comajoan Cara, Alvaro Calafell, Daniel Mas Montserrat, Alexander G. Ioannidis

24. ☆Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces

    Yihuai Hong, Lei Yu, Haiqin Yang, Shauli Ravfogel, Mor Geva

25. ☆Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models

    Theo Putterman, Derek Lim, Yoav Gelberg, Stefanie Jegelka, Haggai Maron

26. ☆Learning on Model Weights using Tree Experts

    Eliahu Horwitz, Bar Cavia, Jonathan Kahana, Yedid Hoshen

27. ☆Mimetic Initialization Helps State Space Models Learn to Recall

    Asher Trockman, Hrayr Harutyunyan, J Zico Kolter, Sanjiv Kumar, Srinadh Bhojanapalli

28. ☆Mimetic Initialization of MLPs

    Asher Trockman, J Zico Kolter

29. ☆Model Assembly Learning with Heterogeneous Layer Weight Merging

    Yi-Kai Zhang, Jin Wang, Xu-Xiang Zhong, De-Chuan Zhan, Han-Jia Ye

30. ☆Model Diffusion for Certifiable Few-shot Transfer Learning

    Fady Rezk, Royson Lee, Henry Gouk, Timothy Hospedales, Minyoung Kim

31. ☆On Symmetries in Convolutional Weights

    Bilal Alsallakh, Timothy J Wroge, Vivek Miglani, Narine Kokhlikyan

32. ☆On the internal representations of graph metanetworks

    Taesun Yeom, Jaeho Lee

33. ☆ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction

    Tong Zhou, Shijin Duan, Gaowen Liu, Charles Fleming, Ramana Rao Kompella, Shaolei Ren, Xiaolin Xu

34. ☆Recursive Self-Similarity in Deep Weight Spaces of Neural Architectures: A Fractal and Coarse Geometry Perspective

    Ambarish Moharil, Indika Kumara, Majid Mohammadi, Damian Andrew Tamburri, Willem-Jan van den Heuvel

35. ☆Scaling Up Parameter Generation: A Recurrent Diffusion Approach

    Kai Wang, Dongwen Tang, Wangbo Zhao, Konstantin Schürholt, Zhangyang Wang, Yang You

36. ☆Shape Generation via Weight Space Learning

    Maximilian Plattner, Arturs Berzins, Johannes Brandstetter

37. ☆Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction

    Léo Meynent, Ivan Melev, Konstantin Schürholt, Goeran Kauermann, Damian Borth

38. ☆TeleLoRA: Teleporting Alignment across Large Language Models for Trojan Mitigation

    Xiao Lin, Manoj Acharya, Anirban Roy, Susmit Jha

39. ☆Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization

    Zexi Li, Lingzhi Gao, Chao Wu

40. ☆The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE

    Andrei Chernov, Oleg Novitskij

41. ☆The Impact of Model Zoo Size and Composition on Weight Space Learning

    Damian Falk, Konstantin Schürholt, Damian Borth

42. ☆The Space Between: On Folding, Symmetries and Sampling

    Michal Lewandowski, Bernhard Heinzl, Raphael Pisoni, Bernhard A. Moser

43. ☆Uncovering Latent Chain of Thought Vectors in Large Language Models

    Jason Zhang, Scott W Viteri

44. ☆Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations

    Uvini Balasuriya Mudiyanselage, Woojin Cho, Minju Jo, Noseong Park, Kookjin Lee

45. ☆Vanishing Feature: Diagnosing Model Merging and Beyond

    Xingyu Qu, Samuel Horváth