Thomas Kollar

thomas-kollar's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 8 months ago

Should VLMs be Pre-trained with Image Data?

Paper • 2503.07603 • Published Mar 10 • 3

authored 3 papers over 1 year ago

OpenVLA: An Open-Source Vision-Language-Action Model

Paper • 2406.09246 • Published Jun 13, 2024 • 41

Language models scale reliably with over-training and on downstream tasks

Paper • 2403.08540 • Published Mar 13, 2024 • 15

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Paper • 2402.07865 • Published Feb 12, 2024 • 15