paper-with-me

Papers

Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality

2025-05-05 · Xueguang Ma, Luyu Gao, Shengyao Zhuang, Jiaqi Samantha Zhan, Jamie Callan, Jimmy Lin

Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created new opportunities for multimodal retrieval. In response, we have updated the Tevatron toolkit, introducing a unified pipeline that enables researchers to explore retriever models at different scales, across multiple languages, and with various modalities. This demo paper highlights the toolkit's key features, bridging academia and industry by supporting efficient training, inference, and evaluation of neural retrievers. We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness, and conduct a cross-modality zero-shot study to demonstrate its research potential. Alongside, we release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval, serving as a baseline for future research.

📄 PDF Abstract BibTeX arXiv:2505.02466

Code (1)

texttron/tevatron 공식 구현 jax

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval

2022-03-11 · Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie Callan

Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of the…

GPURetrieval

MAGMaR Shared Task System Description: Video Retrieval with OmniEmbed

2025-06-11 · Jiaqi Samantha Zhan, Crystina Zhang, Shengyao Zhuang, Xueguang Ma 외

Effective video retrieval remains challenging due to the complexity of integrating visual, auditory, and textual modalities. In this paper, we explore unified retrieval methods using OmniEmbed, a powerful multimodal embe…

RetrievalVideo Retrieval

SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval

2023-07-19 · Nandan Thakur, Kexin Wang, Iryna Gurevych, Jimmy Lin

Traditionally, sparse retrieval systems relied on lexical representations to retrieve documents, such as BM25, dominated information retrieval tasks. With the onset of pre-trained transformer models such as BERT, neural …

Information RetrievalRetrieval

Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval

2023-03-31 · Daniel Campos, ChengXiang Zhai

Vector-based retrieval systems have become a common staple for academic and industrial search applications because they provide a simple and scalable way of extending the search to leverage contextual representations for…

RetrievalTriviaQA

OpenKE: An Open Toolkit for Knowledge Embedding

2018-11-01 · EMNLP 2018 11 · Xu Han, Shulin Cao, Xin Lv, Yankai Lin 외

We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space. OpenKE prioritizes operati…

Information RetrievalKnowledge GraphsQuestion AnsweringRepresentation Learning+1