The authors built OmniSeek around an iterative think, tool-call, observe protocol.
Active audio-visual tool use improves reasoning across long recordings
OmniSeek learns to retrieve targeted audio and video segments over multiple turns, then combines the evidence to answer cross-modal questions.
Big Tech
Haibo Wang · Jiteng Mu · Jialu Li · Jingru Yi · Yuanjun Xiong · Jianming Zhang · +2 more
Adobe Research · University of California Davis
Research Digest··3 min read
Wang and colleagues turn an omni-modal language model into an agent that chooses when to listen, when to look, and which temporal window to inspect.
Why this paper
From Adobe Research and University of California Davis
In one line
OmniSeek improves long-context audio-visual reasoning by letting models iteratively retrieve and combine targeted raw audio and video evidence.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§