A proposed non-attention LLM combining state-space, convolution, recurrence, and retrieval claims near-linear scaling for million-token contexts, with reported benchmark gains unsupported by released artifacts.
Gpt-4 technical report.https://openai.com/research/gpt-4, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
A proposed non-attention LLM combining state-space, convolution, recurrence, and retrieval claims near-linear scaling for million-token contexts, with reported benchmark gains unsupported by released artifacts.