Kosmos-2.5: A Multimodal Literate Model
Paper
•
2309.11419
•
Published
•
55
AI & ML interests
None defined yet.
Papers
FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
GIR-Bench: Versatile Benchmark for Generating Images with Reasoning
JingyeChen
authored
2
papers
over 2 years ago