Streaming video-to-audio (V2A) generation is essential for immersive interactive applications. However, real-time constraints leave existing streaming V2A methods far behind offline models: (1) visual
LiveFoley improves streaming video-to-audio generation by using a trailing sliding window for visual alignment and expanded temporal denoising windows for audio quality with minimal latency.
Streaming video-to-audio (V2A) generation is essential for immersive interactive applications. However, real-time constraints leave existing streaming V2A methods far behind offline models: (1) visual frontends shrink their receptive fields to cut look-ahead latency, severely degrading audio-visual alignment; (2) causal autoregressive diffusion backends denoise each audio patch in isolation, impairing audio quality. To this end, we present LiveFoley, a streaming causal autoregressive diffusion architecture that addresses both bottlenecks with imperceptible latency. For the visual frontend, we introduce a Trailing Sliding Window that converts non-causal segment-level encoders into streaming…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds was first seen on Hugging Face · Daily papers on Nov 6, 2026. Since then it has appeared in 13 checks on 3 different days. Its best position was #29 of 30, reached on Nov 6, 21:28 UTC. It is #29 right now, climbing from #30 to #29 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 17:28 UTC it is #29, climbing from #30 to #29 over the last 6 checks.
#29 on Hugging Face · Daily papers, on Nov 6, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (13 checks) since.