2 papers
cs.CV2026
Efficient Unified Multimodal Understanding (EUMU): Winning Solution for the MUMU Track at the 8th LSVOS Challenge
Dayoung Kil, Seong-heum Kim
The Mobile Unified Multimodal Understanding (MUMU) Challenge requires a single efficient model to jointly perform multi-concept image tagging, open-vocabulary object detection, and…
cs.CV2025
One-Cycle Structured Pruning via Stability-Driven Subnetwork Search
Deepak Ghimire, Dayoung Kil, Seonghwan Jeong +2
Existing structured pruning methods typically rely on multi-stage training procedures that incur high computational costs. Pruning at initialization aims to reduce this burden but…