Shravan Nayak

Hugo Berard

Allison Cohen

Shin (Alexandre) Koseki

Hadrien Bertrand

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

doi.org

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction

Xiangru Jian

Kevin Qinghong Lin

Juan A. Rodriguez

Montek Kalsi

M. Tamer Özsu

David Vazquez

Sai Rajeswar

Human Annotator

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

doi.org

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction

Xiangru Jian

Kevin Qinghong Lin

Juan A. Rodriguez

Montek Kalsi

M. Tamer Özsu

David Vazquez

Sai Rajeswar

Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enh… (see more)ance computer workflows. While existing research focuses on online settings, desktop environments, critical for many professional and everyday tasks, remain underexplored due to data collection challenges and licensing issues. We introduce UI-Vision, the first comprehensive, license-permissive benchmark for offline, fine-grained evaluation of computer use agents in real-world desktop environments. Unlike online benchmarks, UI-Vision provides: (i) dense, high-quality annotations of human demonstrations, including bounding boxes, UI labels, and action trajectories (clicks, drags, and keyboard inputs) across 83 software applications, and (ii) three fine-to-coarse grained tasks—Element Grounding, Layout Grounding, and Action Prediction—with well-defined metrics to rigorously evaluate agents’ performance in desktop environments. Our evaluation reveals critical limitations in state-of-the-art models like UI-TARS-72B, including issues with understanding professional software, spatial reasoning, and complex actions like drag-and-drop. These findings highlight the challenges in developing fully autonomous computer-use agents. With UI-Vision, we aim to advance the development of more capable agents for real-world desktop tasks.

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

proceedings.mlr.press

CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics

Mehar Bhatia

Xiaofeng Zhang

Verena Rieser

Lisa Anne Hendricks

Sjoerd van Steenkiste

Yash Goyal

Karolina Stanczak

Aishwarya Agrawal

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurate… (see more)ly represent diverse cultural contexts. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit as well as implicit cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that T2I models not only fail to meet the more challenging implicit expectations but also the less challenging explicit expectations. Across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we demonstrate that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, providing actionable directions for developing more culturally informed T2I models and evaluation methodologies.

2025-06-10

ArXiv (preprint)

CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics

Mehar Bhatia

Xiaofeng Zhang

Verena Rieser

Lisa Anne Hendricks

Sjoerd van Steenkiste

Yash Goyal

Karolina Stanczak

Aishwarya Agrawal

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurate… (see more)ly represent diverse cultural contexts. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit as well as implicit cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that T2I models not only fail to meet the more challenging implicit expectations but also the less challenging explicit expectations. Across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we demonstrate that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, providing actionable directions for developing more culturally informed T2I models and evaluation methodologies.

2025-06-10

ICML.cc/2025/Workshop/MoFA (poster)

doi.org

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction

Xiangru Jian

Kevin Qinghong Lin

Juan A. Rodriguez

Montek Kalsi

M. T. ¨Ozsu

David Vazquez

Sai Rajeswar

Human Annotator

2025-03-19

ArXiv (preprint)

LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces

Rashid A. Mushkani

Hugo Berard

Allison Cohen

Shin (Alexandre) Koseki

Hadrien Bertrand

We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment of text-to-image (T2I) models i… (see more)n inclusive urban planning. Developed through a two-year participatory process with 30 community organizations, LIVS encodes diverse spatial preferences across 634 initial concepts, consolidated into six core criteria: Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity, through 37,710 pairwise comparisons. Using Direct Preference Optimization (DPO) to fine-tune Stable Diffusion XL, we observed a measurable increase in alignment with community preferences, though a significant proportion of neutral ratings highlights the complexity of modeling intersectional needs. Additionally, as annotation volume increases, accuracy shifts further toward the DPO-tuned model, suggesting that larger-scale preference data enhances fine-tuning effectiveness. LIVS underscores the necessity of integrating context-specific, stakeholder-driven criteria into generative modeling and provides a resource for evaluating AI alignment methodologies across diverse socio-spatial contexts.

2025-02-27

ArXiv (preprint)

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez

Xiangru Jian

Akshay Kalkunte Suresh

Amirhossein Abaskohi

Pierre-Andre Noel

Sanket Biswas … (see 19 more)

Sara Shanian

Sathwik Tejaswi Madhusudhan

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

David Vazquez

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (see more) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to relevant training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure that our data is high quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench,, a benchmark suite with 10 novel tasks where we carefully create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench, improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations revealed that participants preferred the outputs from models trained with BigDocs over those from GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning.

2025-01-22

ICLR.cc/2025/Conference (poster)

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez

Xiangru Jian

Akshay Kalkunte Suresh

Amirhossein Abaskohi

Pierre-Andre Noel

Sanket Biswas … (see 23 more)

Sara Shanian

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi Madhusudhan

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

David Vazquez

Sai Rajeswar

2025-01-22

ICLR.cc/2025/Conference (poster)

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Juan Rodriguez

Xiangru Jian

Akshay Kalkunte

Franccois Savard

Amirhossein Abaskohi

Pierre-Andre Noel

M. L. Richter

Saverio Vadacchino

Shubbam Agarwal

Sanket Biswas … (see 23 more)

Sara Shanian

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Sepideh Kharagani

Sean Hughes

M. Özsu

Issam Hadj Laradji

Spandanna Gella

Perouz Taslakian

David Vazquez

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (see more) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

2024-12-05

ArXiv (preprint)

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Juan Rodriguez

Xiangru Jian

Akshay Kalkunte

Franccois Savard

Amirhossein Abaskohi

Pierre-Andre Noel

Shubbam Agarwal

Sanket Biswas … (see 23 more)

Sara Shanian

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

Spandanna Gella

Perouz Taslakian

David Vazquez

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (see more) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

2024-12-05

ArXiv (preprint)