Cartridges: Lightweight and general-purpose long context representations via self-study · HackerPapers discussions

Cartridges: Lightweight and general-purpose long context representations via self-study — mentioned by jxmorris12

Tue, 21 Oct 2025 18:41:24 GMT

It's great that people are starting to take continual learning seriously, and it seems like Jessy has been thinking about LLMs and continual learning longer than almost anyone. I especially like this taxonomy > I think of continual learning as two subproblems: > Generalization: given a piece of data (user feedback, a piece of experience, etc.), what update should we do to learn the “important bits” from that data? > Forgetting/Integration: given a piece of data, how do we integrate it with what we already know? My personal feeling is that generalization is a data issue: given a datapoint x…

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

Cartridges: Lightweight and general-purpose long context representations via self-study — mentioned by yorwba

Fri, 01 Aug 2025 09:05:10 GMT

> In theory today, I should be able to process <long quote from document> <specific query> and just stop after the long document and save the KV cache right? People do this, it's called prefix caching. There's also https://arxiv.org/abs/2506.06266 where they compress the context down to a smaller representation they call a "cartridge," and composing cartridges from different contexts seems to work reasonably well.

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

Cartridges: Lightweight and general-purpose long context representations via self-study — HN submission

Thu, 26 Jun 2025 20:01:09 GMT

Cartridges: Lightweight long context representations via self-study

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