Rohit Saxena
@rohit-saxena.bsky.social
PhD student at University of Edinburgh
Long Context | Summarization | Vision and Language | Narratives
https://saxenarohit.github.io/
Long Context | Summarization | Vision and Language | Narratives
https://saxenarohit.github.io/
Can multimodal LLMs truly understand research poster images?📊
🚀 We introduce PosterSum—a new multimodal benchmark for scientific poster summarization!
📂 Dataset: huggingface.co/datasets/rohitsaxena/PosterSum
📜 Paper: arxiv.org/abs/2502.17540
🚀 We introduce PosterSum—a new multimodal benchmark for scientific poster summarization!
📂 Dataset: huggingface.co/datasets/rohitsaxena/PosterSum
📜 Paper: arxiv.org/abs/2502.17540
March 10, 2025 at 2:19 PM
Can multimodal LLMs truly understand research poster images?📊
🚀 We introduce PosterSum—a new multimodal benchmark for scientific poster summarization!
📂 Dataset: huggingface.co/datasets/rohitsaxena/PosterSum
📜 Paper: arxiv.org/abs/2502.17540
🚀 We introduce PosterSum—a new multimodal benchmark for scientific poster summarization!
📂 Dataset: huggingface.co/datasets/rohitsaxena/PosterSum
📜 Paper: arxiv.org/abs/2502.17540