AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Unlocking Cross-Modal Biosignal Synthesis: A Temporally-Aware VAE-Diffusion Model

Chenyang Xu, Dezhen Wang, Hao Wang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools

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
remove Enhanced Condition Fusion (cross-attention multi-scale ECG conditioning) (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.760 -> 0.810 (adding fusion)Improved
add Temporal Attention blocks (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.719 -> 0.810Improved
add VAE loss during Phase 3 joint fine-tuning (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.686 -> 0.810Improved
use staged three-phase training instead of training jointly from the start (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.671 -> 0.810Improved
diffuse in VAE latent space instead of raw waveform space (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.662 -> 0.810Improved
use cross-attention fusion instead of concatenation (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setS1 location error (ms): 14.5 -> 12.0Improved
use cross-attention fusion instead of concatenation (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test setS1 detection rate (%): 95.13 -> 95.95No clear effect
inject ECG condition only in the encoder path versus symmetric injection (ablation)Temporally-Aware VAE-Diffusion · EPHNOGRAM test settiming and perceptual qualityNo clear effect
use the proposed VAE-Diffusion instead of a generic two-stage AudioLDM-style latent diffusionTemporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.740 -> 0.810Improved
replace U-Net with matched DiT-style transformer denoiserTemporally-Aware VAE-Diffusion · EPHNOGRAM test setPearson correlation: 0.810 -> 0.792Hurt
evaluate zero-shot on pathological versus normal recordingsTemporally-Aware VAE-Diffusion · PhysioNet/CinC 2016 training-a/MITHSDBPearson correlation: 0.77 -> 0.73Hurt
use DDIM sampling with 50 steps instead of 200-step DDPM (ablation)Temporally-Aware VAE-Diffusion · inference latencylatency (ms): 215.3 -> approximately 54Improved

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