2 citations · 2 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
Xuhui Zhan, Tyler Derr
Connecting pretrained vision and language models usually involves projecting image features into the language model's input space. Inverse-LLaVA reverses this mapping within decode…
cs.CV2025
Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment
Yang Hu, Runchen Wang, Stephen Chong Zhao +4
We introduce Perceptual-Initialization (PI), a paradigm shift in visual representation learning that incorporates human perceptual structure during the initialization phase rather…