VILA: On Pre-training for Visual Language Models
Ji Lin, Hongxu Yin, Wei Ping, Pavlo A. Molchanov, Mohammad Shoeybi, Song Han
Who it is from
Nvidiaaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsNvidia · 925 citations
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action ModelsNvidia · 723 citations
- Neural operators for accelerating scientific simulations and designNvidia · 678 citations
- Small Language Models are the Future of Agentic AIGeorgia Institute of Technology · 628 citations
- Foundation models in robotics: Applications, challenges, and the futureNvidia · 583 citations
- FlashInfer: Efficient and Customizable Attention Engine for LLM Inference ServingNvidia · 452 citations