4 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…
Massive Sound Embedding Benchmark (MSEB)
Georg Heigold, Ehsan Variani, Tom Bagby +4
Audio is a critical component of multimodal perception, and any truly intelligent system must demonstrate a wide range of auditory capabilities. These capabilities include transcri…
Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
Dingmin Wang, Ji Ma, Shankar Kumar
The success of expanded context windows in Large Language Models (LLMs) has driven increased use of broader context in retrieval-augmented generation. We investigate the use of LLM…
JIR-Arena: The First Benchmark Dataset for Just-in-time Information Recommendation
Ke Yang, Kevin Ros, Shankar Kumar Senthil Kumar +1
Just-in-time Information Recommendation (JIR) is a service designed to deliver the most relevant information precisely when users need it, , addressing their knowledge gaps with mi…