Pretrained Transformers as Universal Computation Engines

by   Kevin Lu, et al.

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning – in particular, without finetuning of the self-attention and feedforward layers of the residual blocks. We consider such a model, which we call a Frozen Pretrained Transformer (FPT), and study finetuning it on a variety of sequence classification tasks spanning numerical computation, vision, and protein fold prediction. In contrast to prior works which investigate finetuning on the same modality as the pretraining dataset, we show that pretraining on natural language improves performance and compute efficiency on non-language downstream tasks. In particular, we find that such pretraining enables FPT to generalize in zero-shot to these modalities, matching the performance of a transformer fully trained on these tasks.


page 1

page 7


Knowledge-Aware Language Model Pretraining

How much knowledge do pretrained language models hold? Recent research o...

Investigating Efficiently Extending Transformers for Long Input Summarization

While large pretrained Transformer models have proven highly capable at ...

Study of positional encoding approaches for Audio Spectrogram Transformers

Transformers have revolutionized the world of deep learning, specially i...

NormFormer: Improved Transformer Pretraining with Extra Normalization

During pretraining, the Pre-LayerNorm transformer suffers from a gradien...

Vector-quantized Image Modeling with Improved VQGAN

Pretraining language models with next-token prediction on massive text c...

Verb Knowledge Injection for Multilingual Event Processing

In parallel to their overwhelming success across NLP tasks, language abi...

Mining Knowledge for Natural Language Inference from Wikipedia Categories

Accurate lexical entailment (LE) and natural language inference (NLI) of...

Code Repositories


Official codebase for Pretrained Transformers as Universal Computation Engines.

view repo