InternVL 1.5 Collection A Pioneering Open-Source Alternative to GPT-4V • 8 items • Updated about 21 hours ago • 8
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites Paper • 2404.16821 • Published Apr 25 • 53
InternVL 2.0 Collection Expanding Performance Boundaries of Open-Source MLLM • 17 items • Updated about 1 hour ago • 79
InternVL 1.0 Collection Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks • 16 items • Updated about 21 hours ago • 15