Gelato - From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents
Anas Awadalla*, Dhruba Ghosh*, Aylin Akkus*, Yuhui Zhang, Marianna Nezhurina, Jenia Jitsev, Yejin Choi, Ludwig Schmidt. 2025.
Publications
Data or Language Supervision: What Makes CLIP Better than DINO?
Yiming Liu*, Yuhui Zhang*, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy. EMNLP Findings 2025.
Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models
Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt. 2025.
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, et al.. NeurIPS Datasets and Benchmarks Track 2024.
Why are Visually-Grounded Language Models Bad at Image Classification?
Yuhui Zhang, Alyssa Unell, Xiaohan Wang, Dhruba Ghosh, Yuchang Su, Ludwig Schmidt, Serena Yeung-Levy. NeurIPS 2024.
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Agneet Chatterjee*, Gabriela Stan*, Estelle Aflalo, Sayak Paul, Dhruba Ghosh, Tejas Gokhale, Ludwig Schmidt, Hannaneh Hajishirzi, Vasudev Lal, Chitta Baral, Yezhou Yang. European Conference on Computer Vision 2024.
GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
Dhruba Ghosh, Hanna Hajishirzi, Ludwig Schmidt. NeurIPS Datasets and Benchmarks Track 2023.
DataComp: In search of the next generation of multimodal datasets
Samir Gadre, Gabriel Ilharco, Alex Fang, et al.. NeurIPS Datasets and Benchmarks Track 2023.
The effect of model size on worst-group generalization
Alan Pham*, Eunice Chan*, Vikranth Srivatsa*, Dhruba Ghosh*, Yaoqing Yang, Yaodong Yu, Ruiqi Zhong, Joseph E. Gonzalez, Jacob Steinhardt. NeurIPS DistShift Workshop 2021.
An infrared spectral biomarker accurately predicts neurodegenerative disease class in the absence of overt symptoms
Lila Lovergne*, Dhruba Ghosh*, Renaud Schuck*, Aris A. Polyzos*, Andrew D. Chen, Michael C. Martin, Edward S. Barnard, James B. Brown, Cynthia T. McMurray. Scientific Reports 2021.
Are larger pretrained language models uniformly better? Comparing performance at the instance level
Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt. ACL Findings 2021.