Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and omni training data. We ask whether a model
SleuthVLM uses a vision-language model with transcribed speech and autonomous video sleuthing to outperform direct audio-hearing omni models on long-video benchmarks, showing that agentic reasoning matters more than auditory input.
Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and omni training data. We ask whether a model needs to hear the audio directly at all, and present SleuthVLM, an agent harness built on a VLM that never hears the audio directly: speech will be transcribed into text, and the VLM will sleuth the video on its own without any predefined workflow. On four omni benchmarks with videos up to 90 minutes, SleuthVLM achieves the best average accuracy: 75.0%, 2.6 points above Gemini 3.8 Flash, and it also tops the Video-MME-v2 leaderboard with 77.8%; with an open-source 27B VLM, it beats all…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding? was first seen on Hugging Face · Daily papers on Nov 5, 2026. Since then it has appeared in 9 checks on 2 different days. Its best position was #28 of 30, reached on Nov 5, 13:28 UTC. It dropped off the list after Nov 6, 07:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 6, 07:28 UTC, after 2 days of trending.
#28 on Hugging Face · Daily papers, on Nov 5, 13:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 2 days (9 checks) since.