flow666

/

MLLM-4D

like 1

Hi! I'm Niels from the Hugging Face community team. This PR adds a model card for MLLM-4D, which includes:

• Metadata for the video-text-to-text pipeline and transformers library.
• Links to the paper and official GitHub repository.
• A brief description of the model's capabilities in 4D spatiotemporal reasoning.
• Sample usage instructions for running inference as found in the repository.
• Citation information for the paper.