Peter Grasch

机构：Taoyuan Chang Gung Memorial Hospital, Apple (United Kingdom)

发表论文 10 篇 · 总被引 92 次 · h-index 3

代表论文

• MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training (2024 · Lecture notes in computer science · 被引 52)
• FastVLM: Efficient Vision Encoding for Vision Language Models (2025 · 被引 23)
• MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training (2024 · arXiv (Cornell University) · 被引 11)
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs (2025 · 被引 2)
• FastVLM: Efficient Vision Encoding for Vision Language Models (2024 · arXiv (Cornell University) · 被引 1)
• MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning (2024 · arXiv (Cornell University) · 被引 1)