Ali Hatamizadeh
@ahatamiz1
LLM Tech Lead & Staff Research Scientist @NVIDIA
Co-creator of Gated DeltaNet & Gated DeltaNet-2
가입 June 2015
180 팔로잉 중 4.1K 팬
I think we should literally stop calling every linear model as an SSM.
Mamba2: Sₜ = αₜSₜ₋₁ + kₜvₜᵀ
GDN: Sₜ = αₜ(I − βₜkₜkₜᵀ)Sₜ₋₁ + βₜkₜvₜᵀ
GDN-2: Sₜ = (I − kₜ(bₜ⊙kₜ)ᵀ)DₜSₜ₋₁ + kₜ(wₜ⊙vₜ)ᵀ
GDN family is a gradient step on a local regression loss, not a discretized ODE.
Umbrella term should be "linear RNNs", with SSMs as one sub-family.
더 보기
