InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2402.04617/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTInfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory — mentioned by throwaway888abchttps://news.ycombinator.com/item?id=40015172urn:hackerpapers:mention:2402.04617:40015172Fri, 12 Apr 2024 17:04:36 GMT<p>Paper: InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory https://arxiv.org/abs/2402.04617</p><p><a href="https://hackerpaper.kaipfister.de/p/2402.04617/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL