Sor0ush's picture
|
download
raw
746 Bytes

SVC reproduction bundle

Scripts and outputs for reproducing Singular Value Calibration (SVC) from When Shared Knowledge Hurts (ICML 2026, arXiv:2602.05536).

Quick start

uv sync   # or: pip install -r requirements from environment.yml
python download_checkpoints.py
uv run python verify_repro.py

What this verifies

  • Claim 1: SVC direction preservation (cosine sim ≈ 1)
  • Claim 5: spectral overlap / singular-value gap plots (plot_figure3.png, plot_figure4.png)
  • Claim 6: layer-wise SVD calibration timing
  • Synthetic forward pass through merged encoder + classification head

Not included: full Table 1/2 accuracy evaluation (needs vision datasets / NLP models).

Author repo: https://github.com/lyymuwu/SVC

Xet Storage Details

Size:
746 Bytes
·
Xet hash:
039d4f2bdc92c065e54ecf1379a3a21646a862526d15012414b8f4a44844e8f1

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.