ATLAS: Learning to Optimally Memorize the Context at Test Time · HackerPapers discussions

ATLAS: Learning to Optimally Memorize the Context at Test Time — mentioned by carlovalenti

Tue, 28 Apr 2026 11:09:29 GMT

don't miss the (formerly over-hyped) Google Research's Titans+Atlas thread, they are quite inspiring and informative on the subject; even if I don't think they released anything (open, at least) as a follow-up to their research. https://arxiv.org/abs/2501.00663 https://arxiv.org/abs/2505.23735

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

ATLAS: Learning to Optimally Memorize the Context at Test Time — mentioned by psb217

Thu, 08 Jan 2026 10:48:34 GMT

Per your point 4, some current hyped work is pushing hard in this direction [1, 2, 3]. The basic idea is to think of attention as a way of implementing an associative memory. Variants like SDPA or gated linear attention can then be derived as methods for optimizing this memory online such that a particular query will return a particular value. Different attention variants correspond to different ways of defining how the memory produces a value in response to a query, and how we measure how well the produced value matches the desired value. Some of the attention-like ops proposed in this new…

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

ATLAS: Learning to Optimally Memorize the Context at Test Time — mentioned by SilverSlash

Mon, 08 Dec 2025 00:29:55 GMT

The newer one is from late May: https://arxiv.org/abs/2505.23735

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

ATLAS: Learning to Optimally Memorize the Context at Test Time — HN submission

Sat, 31 May 2025 14:13:00 GMT

Atlas: Learning to Optimally Memorize the Context at Test Time

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