collaborators

7 papers

cs.CV2026

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…

cs.IR2026

On the Theoretical Limitations of Embedding-Based Retrieval

Orion Weller, Michael Boratko, Iftekhar Naim +1

Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, an…

cs.IR2026

Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders

Benjamin Rozonoyer, Chong You, Michael Boratko +5

The success of Large Language Models (LLMs) has motivated a shift toward generative approaches to retrieval and ranking, aiming to supersede classical Dual Encoders (DEs) and Cross…

cs.LG2026

Mining Generalizable Activation Functions

Alex Vitvitskyi, Michael Boratko, Matej Grcic +3

The choice of activation function is an active area of research, with different proposals aimed at improving optimization, while maintaining expressivity. Additionally, the activat…

cs.CL2025

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…

cs.CL2025

Gemini Embedding: Generalizable Embeddings from Gemini

Jinhyuk Lee, Feiyang Chen, Sahil Dua +44

In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini…