AI Paper Atlas

Research map / Video / Video generation

AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation

Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov, Alper Canberk, Kwot Sin Lee, Vicente Ordonez, Sergey Tulyakov

ICCV 2025 · Video › Video generation · approach: Video-to-audio synthesis · 18 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
fix conditioning flow time instead of uniform sampling (ablation)AV-Link V2A · VGGSounds V2A ablationFAD: 6.91 -> 4.79Improved
fix conditioning flow time instead of uniform sampling (ablation)AV-Link V2A · VGGSounds V2A ablationFD: 27.33 -> 18.91Improved
use frozen diffusion features instead of CLIP features (ablation)AV-Link V2A · VGGSounds V2A ablationOnset ACC: 0.386 -> 0.415Improved
use frozen diffusion features instead of CLIP features (ablation)AV-Link V2A · VGGSounds V2A ablationFAD: 2.49 -> 4.79Hurt
use frozen diffusion features instead of CAVP features (ablation)AV-Link V2A · Movie Gen benchmarkIS: 4.62 -> 6.53Improved
add symmetric feature reinjection to Fusion Blocks (ablation)AV-Link V2A · VGGSounds V2A ablationFAD: 6.60 -> 4.79Improved
add symmetric feature reinjection to Fusion Blocks (ablation)AV-Link V2A · VGGSounds V2A ablationOnset ACC: 0.365 -> 0.415Improved
use Fusion Blocks instead of direct alignment (ablation)AV-Link V2A · VGGSounds V2A ablationOnset ACC: 0.283 -> 0.415Improved
use self-attention Fusion Blocks instead of symmetric cross attention (ablation)AV-Link V2A · VGGSounds V2A ablationFAD: 8.47 -> 4.79Improved
use Fusion Blocks instead of concatenation to text with fine-tuning (ablation)AV-Link V2A · VGGSounds V2A ablationOnset ACC: 0.355 -> 0.415Improved
interleave Fusion Blocks instead of placing them after block 22 (ablation)AV-Link V2A · VGGSounds V2A ablationFAD: 6.90 -> 4.79Improved
train separate parameters for V2A and A2V instead of joint sharing (ablation)AV-Link V2A · VGGSounds V2A (no text prompt)FAD: 2.19 -> 1.58Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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