MAGMaR (@MAGMaR_workshop) profile picture

MAGMaR

@MAGMaR_workshop

https://teapaw.org/t.co/QB6DYI4EXi Workshop on Multimodal Augmented Generation via MultimodAl Retrieval

Joined January 2025
  • Tweets28
  • Following10
  • Followers27
3Media
Photo by MAGMaR (@MAGMaR_workshop)Photo by MAGMaR (@MAGMaR_workshop)Photo by MAGMaR (@MAGMaR_workshop)
Dr. Nanyun (Violet) Peng is giving a keynote "Towards Self-Improving Multimodal Models" @VioletNPeng
Image from MAGMaR (@MAGMaR_workshop)
Image from MAGMaR (@MAGMaR_workshop)
2
1
8
890
Happening Now! MAGMaR 2026 @aclmeeting in the Old Town Room. Come chat about Multimodal Retrieval and Generation.
Opening Presentation for MAGMaR 2026

ALT Opening Presentation for MAGMaR 2026

2
2
8
1,120
🧵 The MAGMaR 2026 Shared Task results are out! We challenged teams to retrieve relevant videos from a corpus of 110K+ multilingual clips AND generate grounded, persona-driven articles from them. Come see the findings at our workshop at ACL on July 4! arxiv.org/abs/2606.12295
Findings of the MAGMaR 2026 Shared Task

Findings of the MAGMaR 2026 Shared Task

This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR). In this shared task participants submitted...

arxiv.org
1
2
2
4
879
more replies
🤔What we learned abt generation: Humans and automatic metrics don't agree on what's good here. Annotators rewarded systems that said "I don't have enough evidence to answer that" MiRAGE penalized them for it. Figuring out how to evaluate appropriate refusal is a clear next step
1
2
43
No system in this track uses task-specific fine-tuning, and every system converts videos to text before reasoning. Multi-video reasoning has lots of room for improvement.
2
2
253
Just over a week and a half until the MAGMaR 2026 Workshop at @aclmeeting We look forward to seeing you in San Diego! nlp.jhu.edu/magmar/
1
2
1
3
1,215
Nanyun (Violet) Peng @VioletNPeng is giving a Keynote entitled "Towards Self-Improving Multimodal Models" Chenliang Xu's keynote will be "Multi-level Alignment in Audio-Visual Scene Generation and Learning" @ChenliangXu
1
26
⏰ Deadline extended! The submission deadline for MAGMaR 2026 is now April 15. Don’t miss your chance to share work on multimodal retrieval & generation at ACL 2026! 🚀 👉 nlp.jhu.edu/magmar/ Shared Tasks (Retrieval, Generation, & RAG) are April 20th! See you in San Diego!
2
3
693
📹 + 🧠 + 📝 = 🔥 First call for MAGMaR 2026, the 2nd workshop on multimodal augmented generation via multimodal retrieval! If #RAG isn't hard enough for you, try multilingually and multimodally. Collocated with @aclmeeting in San Diego in July. nlp.jhu.edu/magmar/
1
2
3
8
3,192
This year's shared task allows you to submit for the retrieval track, generation track, or full RAG track on a challenging new collection of unedited ("raw") videos. Research Papers (Apr. 1) Shared Task (Apr. 20)
1
1
115
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). openreview.net/group?id=aclw…

ACL 2025 Workshop MAGMaR

Welcome to the OpenReview homepage for ACL 2025 Workshop MAGMaR

openreview.net
1
3
1
383
teapaw.org/MAGMaR_workshop/status…
MAGMaR (@MAGMaR_workshop) profile pictureMAGMaR@MAGMaR_workshop29 Apr 2025
🚨 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! eval.ai/web/challenges/chall…

EvalAI: Evaluating state of the art in AI

EvalAI is an open-source web platform for organizing and participating in challenges to push the state of the art on AI tasks.

eval.ai
1
106
UPDATE: Shared task paper deadline is **5/20**, not 5/9!
1
61
🚨 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! eval.ai/web/challenges/chall…

EvalAI: Evaluating state of the art in AI

EvalAI is an open-source web platform for organizing and participating in challenges to push the state of the art on AI tasks.

eval.ai
5
3
4
1,894
Load more