10 papers that let you run serious AI locally, starting with the Transformer
alex_verem · x · 2026-10-13
alexverem kicked off a thread titled "Local AI is the future" listing 10 research papers that let anyone run a serious AI model on their own computer today. Entry #1 is Google's 2017 paper Attention Is All You Need, which introduced the Transformer — the architecture every downloadable model today is built on. It relies purely on attention, scored 28.4 BLEU on WMT 2014 En-De and a then-record 41.8 BLEU on En-Fr.
Related event: 10 Papers to Run Serious AI Models Locally Today(2 posts)→
More from Research
- Automated research still needs a million research-years, but simulation advantages are real, researcher argues — gleech · 2026-10-13
- SonicBoom: A Python-Free C++ Runtime Beats llama.cpp Decode by 14% on a Laptop 3050 — nalaginrut · 2026-10-13
- NeurIPS paper: video diffusion models encode physics internally even when outputs are wrong — katjahofmann · 2026-10-13
- Parallel sampling beats sequential self-refinement for scaling LLM accuracy, paper finds — burkov · 2026-10-13
- CrossTimeEdit: Decade-Spanning Dataset and Reward-Guided Historical Street-View Generation — SunYatsen · 2026-10-13
- W.P. Thurston's classic essay 'On Proof and Progress in Mathematics' (PDF) — FrnkNlsn · 2026-10-13