Congrats! Looks like time is a big failure case for these models (cc @neuralnoise.com @aryopg.bsky.social @rohit-saxena.bsky.social )
bsky.app/profile/emil...

Work done with @neuralnoise.com Frank Keller

We tested state-of-the-art multimodal LLMs on this challenging task—and they struggled! 🤖📉

We also propose a new method:
🔥SEGMENT & SUMMARIZE, a training-free approach that outperforms existing models by:
🔹 Segmenting the poster into logical regions
🔹 Performing local & global summarization

📊 PosterSum features 16,305 poster-abstract pairs from major ML conferences.

Task: Summarize a research poster image into a concise abstract summary.

🙋‍♂️

I'd love to be added!
Thanks

Would love to be added!

Hello, can you please add me? Thanks

I'd love to be added!
Thanks