https://sparsenotes.com/series/weekly-papers-2026-05-30/ Recent content in weekly-papers-2026-05-30 on Sparse Notes https://sparsenotes.com/images/og-default.png https://sparsenotes.com/images/og-default.png Hugo -- gohugo.io Sat, 30 May 2026 00:00:00 +0000 https://sparsenotes.com/posts/2026/05/papers/attention-is-all-you-need/ Sat, 30 May 2026 00:00:00 +0000 https://sparsenotes.com/posts/2026/05/papers/attention-is-all-you-need/ The 2017 Vaswani et al. paper that introduced the Transformer — replacing recurrence and convolution with stacked self-attention, and quietly becoming the substrate for nearly every frontier model of the decade that followed. https://sparsenotes.com/posts/2026/05/papers/bounded-memory-generation/ Sat, 30 May 2026 00:00:00 +0000 https://sparsenotes.com/posts/2026/05/papers/bounded-memory-generation/ Kleinberg, Mehrotra, and Saberi extend the classical theory of language generation in the limit to learners with bounded memory — showing that generation remains achievable for every countable collection, while density and identification collapse to finite collections. https://sparsenotes.com/posts/2026/05/papers/rim-working-memory/ Sat, 30 May 2026 00:00:00 +0000 https://sparsenotes.com/posts/2026/05/papers/rim-working-memory/ Aichberger and Hochreiter propose RiM, a latent reasoning method that replaces autoregressively generated chain-of-thought tokens with fixed memory blocks processed in a single forward pass — matching or exceeding existing latent reasoning methods while decoupling internal computation from external communication. https://sparsenotes.com/posts/2026/05/papers/ Sat, 30 May 2026 00:00:00 +0000 https://sparsenotes.com/posts/2026/05/papers/ Three short notes from the May 24–30 paper digest: one Seminal Paper of the Week (Attention Is All You Need) plus the two strongest picks of the week (Reasoning in Memory and Bounded-Memory Language Generation).