Preprint2023
PaLI-3
Unknown
A 5B vision-language model using a 2B SigLIP vision encoder and 3B UL2 language model achieves SOTA on video QA without any video pretraining.
0Oct 1, 2023BenchmarksComputer Vision
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
A 5B vision-language model using a 2B SigLIP vision encoder and 3B UL2 language model achieves SOTA on video QA without any video pretraining.
Neha Yadav, S. Pande, A. Ranjith kumar
Combines SigLIP vision model and Gemma language model following PaLI-3 recipe for strong vision-language task performance.