ICCV Poster "multimodal models" Papers
2 papers found
LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs
Hanyu Zhou, Gim Hee Lee
ICCV 2025posterarXiv:2503.06934
2
citations
VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
Sihan Yang, Runsen Xu, Chenhang Cui et al.
ICCV 2025posterarXiv:2508.05211
3
citations