Hadi Pouransari

发表论文 76 篇 · 总被引 540 次 · h-index 13

代表论文

• SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding (2024 · 被引 92)
• MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training (2024 · 被引 42)
• FastVLM: Efficient Vision Encoding for Vision Language Models (2025 · 被引 23)
• DataComp-LM: In search of the next generation of training sets for language models (2024 · arXiv (Cornell University) · 被引 7)
• CLIP with Quality Captions: A Strong Pretraining for Vision Tasks (2024 · arXiv (Cornell University) · 被引 2)
• Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum (2024 · 被引 2)