Lifeboat Foundation

Buildings collapse in Hualien, as multiple aftershocks reported in Taipei.

Intel presents LLaVA-Gemma.

Accelerating Multimodal Foundation Models with a Compact Language Model https://huggingface.co/papers/2404.

We train a suite of multimodal foundation models (MMFM) using the popular LLaVA framework with the recently released Gemma family of large language models…

Continue reading “Paper page — LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model” »

Google announces Bigger is not Always Better.

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency.

Join the discussion on this paper page.

Meta is paying creators with a “Spring Bonus” and “Performance Bonus” – offering some the potential to earn thousands of dollars.

A woman found that her image was being used in “deepfake porn” and the person responsible was a friend.

Google announces Streaming Dense Video Captioning.

An ideal model for dense video captioning — predicting captions localized temporally in a video — should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to…

Join the discussion on this paper page.

Shared with Dropbox.

Thanks to a new design, the operation time for the plasma torch was extended.

After a rare captivity birth, a family of endangered siamang gibbons were “heard singing together” to celebrate the new arrival.