1.2k citations · 1.7k across the 12 of their papers we have counts for
13 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…
Position: Introspective Experience from Conversational Environments as a Path to Better Learning
Claudiu Cristian Musat, Jackson Tolins, Diego Antognini +3
Current approaches to AI training treat reasoning as an emergent property of scale. We argue instead that robust reasoning emerges from linguistic self-reflection, itself internali…
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…
Entity Image and Mixed-Modal Image Retrieval Datasets
Cristian-Ioan Blaga, Paul Suganthan, Sahil Dua +6
Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a no…
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…
Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
Imad Eddine Toubal, Aditya Avinash, Neil Gordon Alldrin +10
From content moderation to wildlife conservation, the number of applications that require models to recognize nuanced or subjective visual concepts is growing. Traditionally, devel…
CARLS: Cross-platform Asynchronous Representation Learning System
Chun-Ta Lu, Yun Zeng, Da-Cheng Juan +13
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge make…
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Chao Jia, Yinfei Yang, Ye Xia +7
Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human anno…
Unifying Specialist Image Embedding into Universal Image Embedding
Yang Feng, Futang Peng, Xu Zhang +7
Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero…
Graph-RISE: Graph-Regularized Image Semantic Embedding
Da-Cheng Juan, Chun-Ta Lu, Zhen Li +7
Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this p…
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
Alina Kuznetsova, Hassan Rom, Neil Alldrin +9
We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection. The images have a Creativ…
Blockout: Dynamic Model Selection for Hierarchical Deep Networks
Calvin Murdock, Zhen Li, Howard Zhou +1
Most deep architectures for image classification--even those that are trained to classify a large number of diverse categories--learn shared image representations with a single mod…
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
Jonathan Krause, Benjamin Sapp, Andrew Howard +5
Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the for…