Francesco Locatello, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work shows how representations learned from these neural modules can be translated between different pre-trained networks via simpler transformations than previously thought. An advantage of this approach is the ability to estimate these transformations using standard, well-understood algebraic procedures that have closed-form solutions. Our method directly estimates a transformation between two given latent spaces, thereby enabling effective stitching of encoders and decoders without additional training. We extensively validate the adaptability of this translation procedure in different experimental settings: across various trainings, domains, architectures (e.g., ResNet, CNN, ViT), and in multiple downstream tasks (classification, reconstruction). Notably, we show how it is possible to zero-shot stitch text encoders and vision decoders, or vice-versa, yielding surprisingly good classification performance in this multimodal setting.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.00664")
get_code_for_paper("2311.00664")
have("2311.00664")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2311.00664.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2311.00664)
Connect an agent — have() is free.