🛰️ Daily AI Frontier
‹ back to 2026-08-04

Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

Research Efficiency & Systems

Ranking

Overall 67
Content 80
Popularity 36

Observed public metrics from 1 member.

Representative image for Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

Merged summary

TL;DR - PRECOG pre-encodes document corpora offline into State-Space Model hidden states and injects the best-matching state at query time, collapsing RAG prefill cost from O(L_context) to O(1). It matters because it turns retrieval-augmented generation on edge hardware from unusable (~27 s) into interactive (<6 ms).

  • Exploits an SSM-specific property: the fixed-size, position-agnostic recurrent hidden state fully summarizes everything read, so retrieved context can be swapped in directly instead of re-ingested in-context.
  • Adds SMC (Structured Memory Consolidation): hierarchical persistent memory with cognitive-domain clustering, an adjustable fidelity-vs-storage dial, O(1) session init, and fusion of episodic, semantic, and retrieved corpus states.
  • Demonstrated on TENNs-LLM, a 1.2B gated-SSM model with a 192 KB hidden state; reported ~4500Ă— prefill speedup while matching in-context RAG answer quality.
  • Authors argue the mechanism is architecturally impossible for Transformer KV-caches, which are position-entangled and grow linearly with context.

Sources (1)

Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

arXiv cs.LG Anusha Madan Gopal, Aras Pirbadian, Kristofor D. Carlson, M Anthony Lewis, Jonathan Tapson 2026-08-03 arXiv:2608.02560
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-21 14:29:00.623246 UTC

TL;DR - PRECOG pre-encodes document corpora offline into State-Space Model hidden states and injects the best-matching state at query time, collapsing RAG prefill cost from O(L_context) to O(1). It matters because it turns retrieval-augmented generation on edge hardware from unusable (~27 s) into interactive (<6 ms).

  • Exploits an SSM-specific property: the fixed-size, position-agnostic recurrent hidden state fully summarizes everything read, so retrieved context can be swapped in directly instead of re-ingested in-context.
  • Adds SMC (Structured Memory Consolidation): hierarchical persistent memory with cognitive-domain clustering, an adjustable fidelity-vs-storage dial, O(1) session init, and fusion of episodic, semantic, and retrieved corpus states.
  • Demonstrated on TENNs-LLM, a 1.2B gated-SSM model with a 192 KB hidden state; reported ~4500Ă— prefill speedup while matching in-context RAG answer quality.
  • Authors argue the mechanism is architecturally impossible for Transformer KV-caches, which are position-entangled and grow linearly with context.
item →