SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel and 1 more
Who it is from
Appleaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem ComplexityApple · 575 citations
- Diffusion Model-Based Image Editing: A SurveyAdobe Systems · 404 citations
- MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced TrainingApple · 173 citations
- FastVLM: Efficient Vision Encoding for Vision Language ModelsApple · 168 citations
- Multimodal Autoregressive Pre-training of Large Vision EncodersApple · 147 citations
- Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language ModelsApple · 138 citations