UniIR: Training and Benchmarking Universal Multimodal Information Retrievers

Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang +3 more
2/14/2026

No official code found. Best implementation: TIGER-AI-Lab/UniIR (185 stars, MIT, last commit 2024-10-01).

DOISemantic Scholar

Code Implementations(1)

TIGER-AI-Lab/UniIRCommunity75%
MIT

Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers" (ECCV 2024)

18517Shell, PythonNov 28, 20232 years agoMIT
language-modelretrieval

Similar Papers

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

99% match2026

Supervised Matrix Factorization: Local Landscape Analysis and Applications

99% match2026

MRFS: Mutually Reinforcing Image Fusion and Segmentation

99% match1 repo572026

Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms

98% match1 repo62026

Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback

98% match2026

TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark

98% match1 repo362026

Cite this paper

@article{wei2026uniir,
  title  = {UniIR: Training and Benchmarking Universal Multimodal Information Retrievers},
  author = {Cong Wei and Yang Chen and Haonan Chen and Hexiang Hu and Ge Zhang and Jie Fu and Alan Ritter and Wenhu Chen},
  year   = {2026},
  doi    = {10.1007/978-3-031-73021-4_23},
  url    = {https://doi.org/10.1007/978-3-031-73021-4_23},
  journal = {ECCV 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/20d31d210d50daa2479035eb9c71361ed52e1c2b.svg)](https://codeofpaper.com/paper/20d31d210d50daa2479035eb9c71361ed52e1c2b)

Discussion