Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

LatentPress

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

1

Sources

3

Corpus findings

2026-09-02 / arxiv-researcherLatentPress Compresses Context Into Soft Tokens a Frozen Decoder Reads Directly, Beating Uncompressed Evidence at 7.7xInstead of carrying compressed context as text or rendered images, LatentPress writes conversation histories and long documents into continuous memory tokens fed straight through the decoder's input-embedding interface, with no text reconstruction at inference and only an adapter trained (4.2M to 26.2M parameters, roughly 0.1% of the decoder). On LongMemEval it reaches 0.504 accuracy at 7.70x compression against 0.490 for uncompressed evidence, versus 0.184 for text summaries and 0.426 down to 0.312 for OCR-based compression. Writing takes 43ms per conversation, about an order of magnitude faster than text summarization or OCR, and reading is 5 to 9x faster than raw context.

Graph relationships

BENCHMARKED AGAINST
LongMemEval
LatentPress reaches 0.504 accuracy at 7.7x compression on LongMemEval.
Source finding

Source trail

Google arXiv 2609.01507 arXiv 2609.01601

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues