LatentPress Compresses Context Into Soft Tokens a Frozen Decoder Reads Directly, Beating Uncompressed Evidence at 7.7x

arXiv 2609.01507·high signalXBlueskyLinkedInCopy link

Instead 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.