1 code implementation • 10 Jul 2023 • Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler
We propose a more efficient training protocol that fits a linear mapping between image and text embeddings of CLIP via a closed-form solution.
1 code implementation • NeurIPS 2023 • Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
That is, the performance on the pre-training tasks deteriorates when fine-tuning on new tasks.
1 code implementation • NeurIPS 2023 • Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.
1 code implementation • 12 Jul 2022 • Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter
Therefore, exploration strategies and learning methods are required that are capable of tracking the steady domain shifts, and adapting to them.
2 code implementations • 24 May 2022 • Fabian Paischer, Thomas Adler, Vihang Patil, Angela Bitto-Nemling, Markus Holzleitner, Sebastian Lehner, Hamid Eghbal-zadeh, Sepp Hochreiter
We propose to utilize a frozen Pretrained Language Transformer (PLT) for history representation and compression to improve sample efficiency.
1 code implementation • NAACL 2022 • Benjamin Minixhofer, Fabian Paischer, Navid Rekabsaz
Our method makes training large language models for new languages more accessible and less damaging to the environment.