# MLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challenge

arXiv: https://arxiv.org/abs/2608.23234 · HTML: https://mlsanity.com/paper/2608.23234/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 9 of its 9 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 9 of 9)

- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation](https://mlsanity.com/paper/2512.10945/) (2025)
- [MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding](https://mlsanity.com/paper/2510.09274/) (2025)
- [LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation](https://mlsanity.com/paper/2510.11063/) (2025)
- [Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding](https://mlsanity.com/paper/2604.26031/) (2026)

## Abstract (arXiv)

In this technical report, we present a training-free framework for audio-guided video object segmentation, which integrates Multimodal Large Language Models (MLLMs) with SAM-based segmentation models. We decompose the task into several stages and identify suitable foundation models for each stage. Without introducing additional model training or task-specific fine-tuning, our approach leverages the strong multimodal reasoning capabilities of MLLMs to model text-visual correspondence and employs SAM-based models for accurate object mask generation. The proposed framework demonstrates the effectiveness of leveraging foundation models for audio-guided video segmentation and achieves competitive performance in the MeViS-Audio Track of the 8th LSVOS Challenge.