Human-inspired Episodic Memory for Infinite Context LLMs · HackerPapers discussions

Human-inspired Episodic Memory for Infinite Context LLMs — HN submission

Thu, 08 May 2025 00:21:21 GMT

Human-Like Episodic Memory for Infinite Context LLMs

27 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Human-inspired Episodic Memory for Infinite Context LLMs — HN submission

Thu, 22 Aug 2024 07:52:12 GMT

Human-Like Episodic Memory for Infinite Context LLMs

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Human-inspired Episodic Memory for Infinite Context LLMs — HN submission

Thu, 01 Aug 2024 20:20:46 GMT

Human-Like Episodic Memory for Infinite Context LLMs

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Human-inspired Episodic Memory for Infinite Context LLMs — mentioned by CGamesPlay

Thu, 25 Jul 2024 04:43:14 GMT

An interesting paper that was recently published that talks about a different approach: Human-like Episodic Memory for Infinite Context LLMs <https://arxiv.org/abs/2407.09450> This wasn't focused on RAG, but there seems to be a lot of crossover to me. Using the LLM to make "episodes" is a similar problem to chunking, and letting the LLM decide the boundary might also yield good results.

Paper and discussion history. A mention is not an endorsement.