Image de couverture de livre

Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Beiser, Alexander, Martinelli, Flavio, Gerstner, Wulfram, Brea, Johanni
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Flat Channels to Infinity in Neural Loss Landscapes
par: Martinelli, Flavio, et autres
Publié: (2025)

Expand-and-Cluster: Parameter Recovery of Neural Networks
par: Martinelli, Flavio, et autres
Publié: (2023)

Kernel Memory Networks: A Unifying Framework for Memory Modeling
par: Iatropoulos, Georgios, et autres
Publié: (2022)

Should Under-parameterized Student Networks Copy or Average Teacher Weights?
par: Şimşek, Berfin, et autres
Publié: (2023)

Emergent rate-based dynamics in duplicate-free populations of spiking neurons
par: Schmutz, Valentin, et autres
Publié: (2023)

Context selectivity with dynamic availability enables lifelong continual learning
par: Barry, Martin, et autres
Publié: (2023)

Automated Hybrid Grounding Using Structural and Data-Driven Heuristics
par: Beiser, Alexander, et autres
Publié: (2025)

Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
par: Beiser, Alexander, et autres
Publié: (2025)

Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
par: Agrawal, Vibhor, et autres
Publié: (2025)

A Reduction of Input/Output Logics to SAT
par: Steen, Alexander
Publié: (2025)

Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning
par: Beiser, Alexander, et autres
Publié: (2025)

Understanding Gated Neurons in Transformers from Their Input-Output Functionality
par: Gerstner, Sebastian, et autres
Publié: (2025)

Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks
par: Bramlage, Lennart, et autres
Publié: (2025)

Shifting Long-Context LLMs Research from Input to Output
par: Wu, Yuhao, et autres
Publié: (2025)

MuLMINet: Multi-Layer Multi-Input Transformer Network with Weighted Loss
par: Seong, Minwoo, et autres
Publié: (2023)

Joint Input and Output Coordination for Class-Incremental Learning
par: Wang, Shuai, et autres
Publié: (2024)

A Novel Technique for Query Plan Representation Based on Graph Neural Nets
par: Chang, Baoming, et autres
Publié: (2024)

Declarative Techniques for NL Queries over Heterogeneous Data
par: Khabiri, Elham, et autres
Publié: (2025)

NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networks
par: Lan, Yi-Shan, et autres
Publié: (2024)

Forecasting Clicks in Digital Advertising: Multimodal Inputs and Interpretable Outputs
par: Gangopadhyay, Briti, et autres
Publié: (2025)

Physics-Informed Neural Networks for Nonlinear Output Regulation
par: Mengozzi, Sebastiano, et autres
Publié: (2025)

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
par: Ji, Yuchen, et autres
Publié: (2025)

On the Structural Limitations of Weight-Based Neural Adaptation and the Role of Reversible Behavioral Learning
par: Konduru, Pardhu Sri Rushi Varma
Publié: (2026)

Leviathan: Decoupling Input and Output Representations in Language Models
par: Batley, Reza T., et autres
Publié: (2026)

Impact of Employing Weather Forecast Data as Input to the Estimation of Evapotranspiration by Deep Neural Network Models
par: Vaz, Pedro J., et autres
Publié: (2024)

Data Augmentation Techniques for Chinese Disease Name Normalization
par: Cui, Wenqian, et autres
Publié: (2025)

Simple Data Augmentation Techniques for Chinese Disease Normalization
par: Cui, Wenqian, et autres
Publié: (2023)

Weighted Grouped Query Attention in Transformers
par: Chinnakonduru, Sai Sena, et autres
Publié: (2024)

Improved Generalization of Weight Space Networks via Augmentations
par: Shamsian, Aviv, et autres
Publié: (2024)

LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
par: Wu, Wenbo, et autres
Publié: (2025)

Learning Characteristics of Reverse Quaternion Neural Network
par: Yamauchi, Shogo, et autres
Publié: (2024)

QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs
par: Zhang, Weijia, et autres
Publié: (2024)

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
par: Li, Junlong, et autres
Publié: (2025)

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
par: Zhang, Xinghua, et autres
Publié: (2024)

Stochastic Weight Sharing for Bayesian Neural Networks
par: Lin, Moule, et autres
Publié: (2025)

Diffusion-Based Neural Network Weights Generation
par: Soro, Bedionita, et autres
Publié: (2024)

A Spiking Neural Network based on Neural Manifold for Augmenting Intracortical Brain-Computer Interface Data
par: Zheng, Shengjie, et autres
Publié: (2022)

Can Local Learning Match Self-Supervised Backpropagation?
par: Zihan, Wu S., et autres
Publié: (2026)

Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
par: Delrocq, Ariane, et autres
Publié: (2026)

Input-Triggered Hardware Trojan Attack on Spiking Neural Networks
par: Raptis, Spyridon, et autres
Publié: (2025)