{"type":"post","id":"t-tech-lime-trains-llms-with-about-15-3b8c2b","slug":"t-tech-lime-trains-llms-with-about-15-3b8c2b","title":"T-Tech LIMe trains LLMs with about 15% fewer FLOPs without worse quality","description":"T-Tech researchers propose Layer-Integrated Memory (LIMe), an attention extension that routes information from earlier Transformer layers into each head.","retrieval_nugget":"T-Tech researchers propose Layer-Integrated Memory (LIMe), an attention extension that routes information from earlier Transformer layers into each head. In experiments on roughly 1-billion-parameter models, they report faster convergence in FLOPs and lower perplexity than a LLaMA-style baseline. The result is a research signal for teams training models, not a demonstrated production-cost reduction.","published_at":"2026-11-11","updated_at":"2026-11-11","record_date":"2026-11-11","date_kind":"published_at","topics":["memory"],"entities":["T-Tech","Layer-Integrated Memory (LIMe)","Gleb Gerasimov","Yaroslav Aksenov","Nikita Balagansky","Viacheslav Sinii","Daniil Gavrilov"],"related_patterns":[],"novelty_label":"new_fact","what_changed":null,"prior_refs":[],"source_url":"https://aclanthology.org/2026.emnlp-main.2641.pdf","source_urls":["https://aclanthology.org/2026.emnlp-main.2641.pdf"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:t-tech-lime-trains-llms-with-about-15-3b8c2b","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/t-tech-lime-trains-llms-with-about-15-3b8c2b/","markdown":"https://newruntime.com/posts/t-tech-lime-trains-llms-with-about-15-3b8c2b.md","json":"https://newruntime.com/posts/t-tech-lime-trains-llms-with-about-15-3b8c2b.json"},"markdown_url":"https://newruntime.com/posts/t-tech-lime-trains-llms-with-about-15-3b8c2b.md","next_reads":[{"type":"topic","path":"/topics/memory/","url":"https://newruntime.com/topics/memory/","title":"Memory","reason":"Explore the memory topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/memory.md","json_url":"https://newruntime.com/topics/memory.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}