Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals

About

This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent grids. It introduces a preliminary continuous-token model built around a one-level Haar DWT/IDWT frontend, a shared coefficient-token layout, optional structural metadata, lightweight modality value adapters, and a shared token-wise encoder-decoder trunk. On Speech Commands, EuroSAT RGB, and DAVIS 2017 data, a dense shared model reaches 39.92 dB audio, 29.37 dB image, and 23.93 dB video PSNR. A matched-rate sweep under continuous latent scalar budgets indicates that the visual gains are not explained solely by latent capacity, while also showing that additive metadata embeddings are not a universal source of improvement. Finally, fixed-rate energy selection provides a strong non-parametric baseline: energy_global improves average PSNR over uniform selection by 16.73 dB for audio, 16.90 dB for images, and 15.86 dB for video under compressed keep ratios. Masked sparse training reaches 34.45 dB video PSNR with 50% of dense tokens. The results support a unified wavelet token schema and sparse token interface, while stopping short of establishing a universal discrete vocabulary.

Shenghao Ding• 2026

Related benchmarks

TaskDatasetResultRank
Video Frame ReconstructionDAVIS 2017 (val)--
8
ReconstructionSpeech Commands (val)
MSE1.02
3
ReconstructionEuroSAT RGB (val)
MSE1.16
3
Signal ReconstructionAudio
PSNR32.6
1
Signal ReconstructionImage
PSNR29.98
1
Signal ReconstructionVIDEO
PSNR34.45
1
Showing 6 of 6 rows

Other info

Follow for update