{"total":50,"papers":[{"id":"arxiv:2405.12250","title":"Your Transformer is Secretly Linear","date":"2024-05-19","section":"LLMs: architectures, context, training","quality":-0.404708,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6ae80c5f07c56011562d6b8323b0984ec0d36194708a43867aae691e2ddc5d86/","source_url":"https://arxiv.org/abs/2405.12250","text_available":true},{"id":"arxiv:2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","date":"2023-12-08","section":"LLMs: architectures, context, training","quality":0.594423,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/baa792b06bdd30f91619f1e852aa5ae4dbf688fe3b1f2ee0722b339b9993ac5c/","source_url":"https://arxiv.org/abs/2312.04927","text_available":true}],"next":null}