Replace a fixed DCT or Fourier transform in transform coding with a trainable isometric tensor-network transform whose local gates are learned once on a dataset. Retain the k coefficients with largest magnitude and reconstruct with the exact adjoint transform; the transform remains norm-preserving and fast while adapting its coefficient ordering to the data distribution.
Combine the very-weak residual with step activations and one-bit weights, so the deployed PDE solver uses threshold and binary operations while training still optimizes a differentiable surrogate. The weak objective only needs values of the trial function and therefore does not require differentiating discontinuous activations with respect to spatial coordinates.
Use a low-rank Tucker reconstruction as a structured backbone and quantize only its residual after an orthogonal rotation. The rotation preserves residual energy but redistributes it across coordinates, reducing dynamic-range imbalance and making 2- or 4-bit uniform quantization less damaging than direct quantization of the original KV tensor.
Paper: A JoLT for the KV cache: Near-lossless KV cache compression via joint Lagrangian allocation of Tucker ranks and a rotated residual for llmsarXiv:2607.12550
Make Laplacian latency attention hardware-friendly by quantizing the exponential decay and row normalization to powers of two. Exponentials and divisions can then be implemented with lookup tables and integer shifts, enabling a low-bit attention kernel for neuromorphic and edge accelerators.