{"total":415,"papers":[{"id":"doi:10.1038/d41586-024-01413-w","title":"Why mathematics is set to be revolutionized by AI","date":"2024-05-14","section":"Reasoning and the \"physics\" of language models","quality":-0.264135,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/75a9d04d59d72d6fd85d0f645fc4eead55088ed0cbbeb433b902596630448dd5/","source_url":"https://doi.org/10.1038/d41586-024-01413-w","text_available":true},{"id":"doi:10.5281/zenodo.21979851","title":"Why the Third Axis Is Freedom","date":"2026-08-01","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ad1cb25a030788de49889f8170798679149cc66d4b4b53060770d5e4069758e9/","source_url":"https://doi.org/10.5281/zenodo.21979851","text_available":true},{"id":"arxiv:2608.11676","title":"XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication","date":"2026-08-12","section":"LLMs: architectures, context, training","quality":0.249727,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a1cbafd1249485a1818a70256d0d3ac5806d55b6900f005e9098c57d37918e44/","source_url":"https://arxiv.org/abs/2608.11676","text_available":true},{"id":"arxiv:2405.04517","title":"xLSTM: Extended Long Short-Term Memory","date":"2024-05-07","section":"LLMs: architectures, context, training","quality":-0.312713,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/40fd3e03894caeb940ad2021fb4052c0d2e809706b5022f7454072997b8ba2d5/","source_url":"https://arxiv.org/abs/2405.04517","text_available":true},{"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":"openreview:XyGJJ4FPoX","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","date":"2022-10-01","section":"Reinforcement learning","quality":-0.454643,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fb4e3bd06740741f593887b474deedc44ad341fa5736c2970e3cc11f065d58de/","source_url":"https://openreview.net/forum?id=XyGJJ4FPoX","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}