← Search

Angela Bitto-Nemling

2 accepted papers

2022

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

NeurIPS 2022accept

CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a foundation model like BERT or GPT3. CLIP vision models that have a rich representation are pre-trained using the InfoNCE objective and natural language supervision before they are fine-tuned on particular tas…

2022

History Compression via Language Models in Reinforcement Learning

ICML 2022spotlight

In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP. We propose to utilize a frozen Pretrained Language Transformer (PLT) for history representation and compression to improve sample efficiency. To avoid tr…