8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020

2020

147 citations recorded by the source corpus.

Citations in the corpus

• What learning algorithm is in-context learning? Investigations with linear models (2022, background): “There are various existing universality results for transformers (Yun et al., 2020; Wei et al., 2021), and for neural networks more generally (Hornik et al., 1989).”
• Human-level play in the game of Diplomacy by combining language models with strategic reasoning (2022, background): “Further, repeated messaging creates feedback loops, in which the language model imitates the style of its own previous messages — for example, send-ingashort or incoherentmessagewillincrease the likelihood of such messages in the future ( 18 ).”
• ResT: An Efficient Transformer for Visual Recognition (2021, background): “Different from CNNs, which can implicitly encode spatial position information by zero-padding [14], the self-attention in Transformers has no ability to distinguish token order in different positions.”