Papers by Andrea Burns
Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large models achieve strong performance on Vision-and-Language Navigation tasks, but are costly to run in resource-limited environments. |
| Approach: | They propose a method to prune large models to minimize information loss . they use navigation-specific traits to filter the model into foreground and background . |
| Outcome: | The proposed method outperforms previous work on standard VLN benchmarks while saving 50% FLOPS. |
Tell Me What’s Next: Textual Foresight for Generic UI Representations (2024.findings-acl)
Copied to clipboard
| Challenge: | Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. |
| Approach: | They propose a pretraining objective for learning UI screen representations using captioning. |
| Outcome: | The proposed approach outperforms state-of-the-art on generation tasks with 28x fewer images. |
A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding (2023.emnlp-main)
Copied to clipboard
Andrea Burns, Krishna Srinivasan, Joshua Ainslie, Geoff Brown, Bryan Plummer, Kate Saenko, Jianmo Ni, Mandy Guo
| Challenge: | Existing datasets for webpages contain only fragments of webpages . generative tasks like page description generation and section summarization are often left unstudied . |
| Approach: | They introduce a Wikipedia Webpage suite that contains 2M pages with all associated image, text, and structure data. |
| Outcome: | The proposed approach performs better than full attention with lower computational complexity. |
ImageInWords: Unlocking Hyper-Detailed Image Descriptions (2024.emnlp-main)
Copied to clipboard
Roopal Garg, Andrea Burns, Burcu Karagol Ayan, Yonatan Bitton, Ceslee Montgomery, Yasumasa Onoe, Andrew Bunner, Ranjay Krishna, Jason Baldridge, Radu Soricut
| Challenge: | generating accurate hyper-detailed image descriptions is challenging for vision-language models trained on web-scraped image-text. |
| Approach: | They propose a data-centric framework for generating hyper-detailed image descriptions using web-scraped image-text. |
| Outcome: | The proposed framework improves on human evaluations on the data, even with only 9k samples. |