Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance

The paper introduces Molmo2Fish, an interactive tool that uses a multimodal large language model to correct imperfect fish tracking predictions in sonar datasets. It demonstrates that the system can effectively improve multi‑object tracking performance through natural language guidance, though further enhancements are needed. The authors provide open‑source code and data for replication.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

• llms
• computer-vision
• multimodal