Unverified60% confidenceFactExact time
In 2023, Gu and Dao proposed Mamba, introducing an input-dependent selective scan mechanism that achieves language modeling performance comparable to or better than Transformers while maintaining linear time complexity.
2
Sources
60%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
UnverifiedThe Mamba state space model was proposed by Albert Gu and Tri Dao in 2023, with both computational complexity and memory usage at O(1) during inference68% similarUnverifiedMamba's memory footprint during inference remains constant and does not grow linearly with sequence length, narrowing the gap with Transformers on language modeling tasks.66% similarUnverifiedThe fusion of Mamba-style state space models with Transformers is moving from papers to usable open-source weights.64% similarUnverifiedMamba's key innovation is making the SSM's B and C matrices and the step size Δ functions of the input, thereby gaining content-aware gating capability while retaining linear complexity.63% similarVerifiedMamba 等基于状态空间模型（SSM）的架构以线性复杂度实现序列建模，更适合实时推理62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/697005API
curl https://kongchang.com/api/v1/knowledge/claims/697005MCP
get_claim(id=697005)