HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
Vista: Enhancing long-duration and high-resolution video understanding by video spatiotemporal augmentation, 2024.https://arxiv.org/abs/2412.00927
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SmolVLM-256M outperforms a 300-times larger model using under 1 GB GPU memory, while the 2.2B version matches state-of-the-art VLMs at half the memory cost.
citing papers explorer
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
-
SmolVLM: Redefining small and efficient multimodal models
SmolVLM-256M outperforms a 300-times larger model using under 1 GB GPU memory, while the 2.2B version matches state-of-the-art VLMs at half the memory cost.