416 citations · 438 across the 9 of their papers we have counts for
3 papers · 1 filter
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces
Hongyuan Tao, Xinggang Wang, Lianghui Zhu +7
We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and quantized images as discrete t…
Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D
Haoxuan Li, Sixu Yan, Lianghui Zhu +3
Vision-Language-Action (VLA) models have demonstrated remarkable generalization in robotic manipulation via large-scale multimodal pretraining. However, VLA models are mainly train…
Mixture-of-Depths Attention
Lianghui Zhu, Yuxin Fang, Bencheng Liao +10
Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers…