Siyu Liao, Xinyu Ding, Bangtian Liu, Zhongfeng Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFFT), cannot achieve true in-place computation. In particular, rFFT maps an input of size n to a complex output of size n/2 + 1, causing dimensional mismatch and requiring additional memory allocation. We propose the first real-domain, fully in-place FFT framework (rdFFT) that preserves input-output memory space consistency. By leveraging butterfly operation symmetry and conjugate properties in the frequency domain, we design an implicit complex encoding scheme that eliminates intermediate cache usage entirely. Experiments on multiple natural language understanding tasks demonstrate the method effectiveness in reducing training memory cost, offering a promising direction for frequency-domain lightweight adaptation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2511.01385")
get_code_for_paper("2511.01385")
have("2511.01385")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2511.01385.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2511.01385)
Connect an agent — have() is free.