AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Few-shot Acoustic Synthesis with Multimodal Flow Matching

Amandine Brunetto

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Rectified flow straightening · 1 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
add geometry conditioning to audio-only model (ablation)FLAC · AcousticRooms unseen roomsFDG: 0.663 -> 0.305Improved
add audio context to geometry-only model (ablation)FLAC · AcousticRooms unseen roomsT60 error (%): 23.41 -> 9.95Improved
use fine-tuned DINOv3 ViT-S/16 instead of xRIR ViT (ablation)FLAC (K=1) · AcousticRooms unseen roomsT60 error (%): 10.91 -> 9.95Improved
freeze DINOv3 weights (ablation)FLAC (K=1) · AcousticRooms unseen roomsR@5 (%): 18.9 -> 15.40Hurt
train DINOv3 from scratch instead of fine-tuning (ablation)FLAC (K=1) · AcousticRooms unseen roomsR@5 (%): 18.9 -> 5.29Hurt
replace ResNet-18 with frozen pretrained VAE encoder for acoustic context (ablation)FLAC (K=1) · AcousticRooms unseen roomsT60 error (%): 9.95 -> 9.40Mixed
AdaLN for target pose and time plus cross-attention for context, versus cross-attention only (ablation)FLAC DiT (K=1) · AcousticRooms unseen roomsT60 error (%): 15.68 -> 9.95Improved
AdaLN+CA versus in-context conditioning (ablation)FLAC DiT (K=1) · AcousticRooms unseen roomsT60 error (%): 69.68 -> 9.95Improved
AdaLN+CA versus in-context conditioning (ablation)FLAC DiT (K=8) · AcousticRooms unseen roomsT60 error (%): 8.12 -> 8.60Hurt
use stochastic generation instead of fixed noise (ablation)FLAC · AcousticRooms unseen roomsT60 error: +6% T60 with deterministic variantImproved
increase guidance weight or number of inference steps (ablation)FLAC · AcousticRooms unseen roomsFDG: 0.305 -> 0.280 (20 steps)Improved
more inference steps (ablation)FLAC · AcousticRooms unseen roomsT60 error (%)No clear effect

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