10 papers
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
Aron Asefaw, Konstantinos Tzevelekakis, Damian Falk +2
Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking…
GeoSANE: Learning Geospatial Representations from Models, Not Data
Joelle Hanna, Damian Falk, Stella X. Yu +1
Recent advances in remote sensing have led to an increase in the number of available foundation models; each trained on different modalities, datasets, and objectives, yet capturin…
Learning Model Representations Using Publicly Available Model Hubs
Damian Falk, Konstantin Schürholt, Konstantinos Tzevelekakis +2
The weights of neural networks have emerged as a novel data modality, giving rise to the field of weight space learning. A central challenge in this area is that learning meaningfu…
A Model Zoo on Phase Transitions in Neural Networks
Konstantin Schürholt, Léo Meynent, Yefan Zhou +3
Using the weights of trained Neural Network (NN) models as data modality has recently gained traction as a research field - dubbed Weight Space Learning (WSL). Multiple recent work…
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou +11
Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate o…
Dense Air Pollution Estimation from Sparse in-situ Measurements and Satellite Data
Ruben Gonzalez Avilés, Linus Scheibenreif, Damian Borth
This paper addresses the critical environmental challenge of estimating ambient Nitrogen Dioxide (NO) concentrations, a key issue in public health and environmental policy. Exi…