Scaling Retrieval-Based Language Models with a Trillion-Token Datastore Paper • 2407.12854 • Published Jul 9 • 29
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use Paper • 2308.06595 • Published Aug 12, 2023 • 5
Language models scale reliably with over-training and on downstream tasks Paper • 2403.08540 • Published Mar 13 • 14
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning Paper • 2402.11690 • Published Feb 18 • 7