@inproceedings{14216,
  abstract     = {CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a huge dataset. LiT improved this by only training the text encoder and using a pre-trained vision network. In this paper, we show that a common space can be created without any training at all, using single-domain encoders (trained with or without supervision) and a much smaller amount of image-text pairs. Furthermore, our model has unique properties. Most notably, deploying a new version with updated training samples can be done in a matter of seconds. Additionally, the representations in the common space are easily interpretable as every dimension corresponds to the similarity of the input to a unique entry in the multimodal dataset. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multi-modal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.},
  author       = {Norelli, Antonio and Fumero, Marco and Maiorca, Valentino and Moschella, Luca and Rodolà, Emanuele and Locatello, Francesco},
  booktitle    = {37th Conference on Neural Information Processing Systems},
  isbn         = {9781713899921},
  location     = {New Orleans, LA, United States},
  pages        = {15303--15319},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {{ASIF: Coupled data turns unimodal models to multimodal without training}},
  volume       = {36},
  year         = {2023},
}

@inproceedings{14953,
  abstract     = {This paper provides statistical sample complexity bounds for score-matching and
its applications in causal discovery. We demonstrate that accurate estimation of the
score function is achievable by training a standard deep ReLU neural network using
stochastic gradient descent. We establish bounds on the error rate of recovering
causal relationships using the score-matching-based causal discovery method of
Rolland et al. [2022], assuming a sufficiently good estimation of the score function.
Finally, we analyze the upper bound of score-matching estimation within the scorebased generative modeling, which has been applied for causal discovery but is also
of independent interest within the domain of generative models.y},
  author       = {Zhu, Zhenyu and Locatello, Francesco and Cevher, Volkan},
  booktitle    = {37th Conference on Neural Information Processing Systems},
  isbn         = {9781713899921},
  issn         = {1049-5258},
  location     = {New Orleans, LA, United States},
  pages        = {3325--3337},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {{Sample complexity bounds for score-matching: Causal discovery and generative modeling}},
  doi          = {10.52202/075280-0147},
  volume       = {36},
  year         = {2023},
}