UPDATE: Shared task paper deadline is **5/20**, not 5/9!.

24 hours left to submit a paper to the Multimodal RAG workshop at #acl2025! We welcome all papers on related topics. Also be sure to check out our shared task (paper deadline 5/9).

🚨 IT'S HERE! 🚨.The Eval Leaderboard is now LIVE! 🏆💻. Our video retrieval collection stumps most pre-trained models. See if you can build a better system!.

Submit here:

🚨 Deadline extension! 🚨. The MAGMaR paper submission date has been extended to May 1, 2025 (archival and non-archival). Show off your multimodal + RAG projects!.

The repository is set for manual approval. If you are not approved within a day, please let us know. The leaderboard will be up by the end of the week. Please feel free to reach out with any questions!.

* CLIP features.* SigLIP features.* Whisper ASR transcripts.* PaddleOCR output.* ICDAR OCR output (Etter et al., 2023).* Florence video captions (test only). The train queries/judgments are also available, along with the test queries.

We are happy to announce the full release of MultiVENT 2.0 through @huggingface!. All train and test videos are provided, subset into tar files of 100 videos. Baseline extracted features are provided as well, including.

RT @EYangTW: July at @aclmeeting, we are organizing MAGMaR -- workshop on multimodal RAG! .We have a shared task on multimodal retrieval an….

We now have a Slack channel for the 2025 Workshop on Multimodal Augmented Generation via Multimodal Retrieval!. This channel will serve as the primary communication method between authors, participants, and organizers:

New Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR) to be held at @aclmeeting ACL in Vienna this summer. We have a new shared task that stumps most LLMs - including ones pretrained on our test collection.