{"ID":5935631,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03551","arxiv_id":"2607.03551","title":"WeightCLIP: Aligning Datasets and Models for Weight Space Learning","abstract":"Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking a way to shape these weight-space representations using information about the datasets the models were trained on, thus limiting downstream applications. We propose WeightCLIP, a method for learning a dataset-aligned latent space for neural networks, where datasets information is induced during training. The NNs are encoded as latent representations using an autoencoder, while dataset samples are encoded using a dataset encoder. The two representations are aligned using a contrastive objective, effectively reshaping the weight-space representations according to the datasets. We demonstrate that such representations can be used for different downstream tasks, including mapping dataset information to a weight-space representation that decode to strong models. In addition, we introduce a latent refinement process for generating models that outperforms standard fine-tuning. Overall, our results demonstrate that explicitly incorporating dataset information improves what can be achieved with weight-space representations across retrieval, generation, and refinement. Code will be available at https://github.com/HSG-AIML/WeightCLIP.","short_abstract":"Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking a way to shape these weight-space representations using information about the datasets the models were trained on, thus limiting downstream...","url_abs":"https://arxiv.org/abs/2607.03551","url_pdf":"https://arxiv.org/pdf/2607.03551v1","authors":"[\"Aron Asefaw\",\"Konstantinos Tzevelekakis\",\"Damian Falk\",\"Léo Meynent\",\"Damian Borth\"]","published":"2026-07-03T18:27:18Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":613923,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T01:22:02.77346169Z","DeletedAt":null,"paper_id":5935631,"paper_url":"https://arxiv.org/abs/2607.03551","paper_title":"WeightCLIP: Aligning Datasets and Models for Weight Space Learning","repo_url":"https://github.com/HSG-AIML/WeightCLIP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}