AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals

Tomoyoshi Kimura, Denizhan Kara, Jinyang Li, Hongjue Zhao, Yigong Hu, Yizhuo Chen, Xiaomin Ouyang, Shengzhong Liu, Tarek F. Abdelzaher

ICML 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace uniform patching with Dywave event-aligned tokenizationMamba2 backbone · PAMAP2 / RWHAR accelerometeraccuracy: RWHAR 0.7340 -> 0.8517Improved
add hierarchical wavelet embedding (vs PatchTST embedding) (ablation)Dywave · MOD audioaccuracy: 0.8520 -> 0.9002Improved
add reconstruction objective (ablation)Dywave · MOD audioaccuracy: 0.7823 -> 0.9002Improved
use similarity-based saliency instead of CNN boundary prediction (ablation)Dywave · MOD audioaccuracy: 0.8064 -> 0.9002Improved
add temporal fusion of non-anchor segments (ablation)Dywave · MOD audioaccuracy: 0.7582 -> 0.9002Improved
add temporal fusion of non-anchor segments (ablation)Dywave · MOD seismicaccuracy: 0.7863 vs 0.7930No clear effect
use embedding-space cosine saliency instead of spectral energy (ablation)Dywave · MOD audioaccuracy: 0.8533 -> 0.9002Improved
use Dywave tokens instead of PatchTST under head-only finetuningTransformer · MOD-Seismic cross-domainaccuracy: 0.3414 -> 0.7565Improved
use Dywave tokens instead of PatchTST under full finetuningTransformer · MOD-Seismic cross-domainaccuracy: 0.8111 -> 0.8119No clear effect
use Dywave instead of dynamic patching baselines LightGTS and RupturesTransformer · RWHARaccuracy: 0.8586 -> 0.9094Improved
use Dywave tokens instead of WaveToken discretization baselineTransformer · MOD seismicaccuracy: 0.5358 -> 0.7917Improved
use Dywave instead of fixed patching, token countTransformer · Ego4D 5s to 30snumber of tokens: PatchTST 59 -> 372 vs Dywave 15.5 -> 35Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy