Unverified50% confidenceFactExact time
SSF-Net's differentiation lies in replacing the fully connected spectral processing commonly used in combinations of Mamba-type structures with Fourier methods by a block-diagonal MLP, thereby compressing the parameter count.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/9/2026
First Seen
Valid until: 2/7/2027
Sources
Related Entities
Related Claims
UnverifiedSSU-LSF is an approximate unlearning method that, targeting the characteristic of the Mamba state transition matrix appearing in matrix exponential form, computes gradients using the closed-form solution of the Fréchet derivative of the matrix exponential.69% similarUnverifiedMamba2 is a sequence modeling architecture based on the state space model (SSM), which binds the SSM state dimension to the input channels and rewrites the per-timestep serial recurrence into matrix multiplication form, allowing parallel computation using GPU Tensor Cores.66% similarUnverifiedOn five large-scale H100 bfloat16 workloads, the authors' fused GPU kernels were roughly on par with Mamba 2 within the SSM core scope.61% similarUnverifiedNVFP4 quantization is not 4-bit for the whole model: the vision encoder, connector, Mamba convolutions, and embedding stay in BF16, and the MoE router stays in FP32.59% similarUnverifiedMamba-2 and hybrid architectures combining Mamba with Transformers (such as Jamba) have been released, alternately stacking attention mechanisms and SSM layers.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150264API
curl https://kongchang.com/api/v1/knowledge/claims/1150264MCP
get_claim(id=1150264)