Efficient Unified Multimodal Understanding (EUMU): Winning Solution for the MUMU Track at the 8th LSVOS Challenge

arXiv:2609.19451 · cs.CV · Submitted 2026-09-16 · Read on arXiv

cs.CV

Submitted: 2026-09-16

Updated: 2026-09-16

Code: https://github.com/Dayoung-Kil/EUMU

Project page: https://lsvos.github.io

Terminology

• Grounding — 8× in this paper · explained in 3 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Efficient Unified Multimodal Understanding — 4× in this paper
• Transformer — 4× in this paper · explained in 2 episodes
• Mobile Unified Multimodal Understanding — 3× in this paper
• Cooperation — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Resource Constraints — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large-scale Video Object Segmentation — 1× in this paper
• National Research Foundation of Korea — 1× in this paper
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models