5 citations · 9 across the 5 of their papers we have counts for
5 papers
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang +86
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage t…
Taking Shortcuts for Categorical VQA Using Super Neurons
Pierre Musacchio, Jaeyi Jeong, Dahun Kim +1
Sparse Attention Vectors (SAVs) have emerged as an excellent training-free alternative to supervised finetuning or low-rank adaptation to improve the performance of Vision Language…
EmbeddingGemma: Powerful and Lightweight Text Representations
Henrique Schechter Vera, Sahil Dua, Biao Zhang +86
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledg…
OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All
Yuanhuiyi Lyu, Xu Zheng, Dahun Kim +1
Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real ma…
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation
Minsu Kim, Jeongsoo Choi, Dahun Kim +1
This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation that can also benefit the transfer of pre-trained knowledge to text-based…