IDEA

2026

1. Three Modalities, Two Design Probes, One Prototype, and No Vision: Experience-Based Co-Design of a Multi-modal 3D Data Visualization Tool

   Sanchita S Kamath, Aziz N Zeidieh, Venkatesh Potluri, Sile O’Modhrain, Kenneth Perry, and 1 more author

   In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, 2026

   Bib

   @inproceedings{kamath26ThreeModalities,
     title = {Three Modalities, Two Design Probes, One Prototype, and No Vision: Experience-Based Co-Design of a Multi-modal 3D Data Visualization Tool},
     author = {Kamath, Sanchita S and Zeidieh, Aziz N and Potluri, Venkatesh and O'Modhrain, Sile and Perry, Kenneth and Seo, JooYoung},
     booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
     pages = {1--23},
     year = {2026},
   }

2. TouchScribe: Augmenting Non-Visual Hand-Object Interactions with Automated Live Visual Descriptions

   Ruei-Che Chang, Rosiana Natalie, Wenqian Xu, Jovan Zheng Feng Yap, Tiange Luo, Venkatesh Potluri, and 1 more author

   In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, 2026

   Bib

   @inproceedings{chang2026touchscribe,
     title = {TouchScribe: Augmenting Non-Visual Hand-Object Interactions with Automated Live Visual Descriptions},
     author = {Chang, Ruei-Che and Natalie, Rosiana and Xu, Wenqian and Yap, Jovan Zheng Feng and Luo, Tiange and Potluri, Venkatesh and Guo, Anhong},
     booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
     pages = {1--18},
     year = {2026},
   }

3. RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People

   Xinyun Cao, Kexin Phyllis Ju, Chenglin Li, Venkatesh Potluri, and Dhruv Jain

   In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, , 2026

   Abs DOI Bib Code

   As virtual 3D environments become more prevalent, equitable access is essential for blind and low-vision (BLV) users, who face challenges with spatial awareness, navigation, and interaction. Prior work has explored supplementing visual information with auditory or haptic modalities, but these methods are static and offer limited support for dynamic, in-context adaptation. Recent advances in generative AI allow users to query and modify 3D scenes via natural language, introducing a paradigm that offers greater flexibility and control for accessibility. We present RAVEN, a system that enables BLV users to issue queries and modification prompts to improve the runtime accessibility of 3D virtual scenes. We evaluated RAVEN with eight BLV people and six Unity developers, generating empirical insights into how conversational programming can support personalized accessibility in 3D environments. Our work highlights both the promise of natural language interaction—intuitive, flexible, and empowering—and the challenges of ensuring reliability, transparency, and trust in generative AI–driven accessibility systems.

   @inproceedings{Cao2026RAVEN,
     author = {Cao, Xinyun and Phyllis Ju, Kexin and Li, Chenglin and Potluri, Venkatesh and Jain, Dhruv},
     title = {RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People},
     year = {2026},
     isbn = {9798400722783},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3772318.3791616},
     doi = {10.1145/3772318.3791616},
     booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
     articleno = {1625},
     numpages = {19},
     keywords = {Accessibility, 3D, blind and low-vision, generative AI},
     location = {
     },
     series = {CHI '26},
   }

4. Vibe Check: Accessibility Heuristics for Vibe Coding Interfaces

   Shalini Madan, Sreelakshmi Surabiyil Bindu, and Venkatesh Potluri

   In Proceedings of the 23rd International Web for All Conference, Dubai, United Arab Emirates , 2026

   Abs DOI Bib

   AI coding tools are transforming programming from a highly editorial task into natural language conversations. Popular vibe coding tools such as Replit and Cursor integrate natural language interfaces with traditional development environments, simplifying software development and increasing productivity through automation. These tools, however, introduce new accessibility challenges for blind or low vision (BLV) developers. These accessibility challenges necessitate comprehensive guidelines that account for the complex interactions in these tools. To address this need, we develop a set of heuristics to assess the accessibility of conversational programming tools. Our heuristics combine web accessibility guidelines, best practices to design conversational interfaces, and accessibility needs specific to BLV developers. A validation study with 16 auditors across two phases with 3 conversational programming tools demonstrates that heuristics are applicable to surface both known accessibility issues and a substantial proportion of novel challenges posed by inaccessible human-AI interactions.

   @inproceedings{Madan2026VibeCheck,
     author = {Madan, Shalini and Surabiyil Bindu, Sreelakshmi and Potluri, Venkatesh},
     title = {Vibe Check: Accessibility Heuristics for Vibe Coding Interfaces},
     year = {2026},
     isbn = {9798400723728},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3800424.3800455},
     doi = {10.1145/3800424.3800455},
     booktitle = {Proceedings of the 23rd International Web for All Conference},
     pages = {229–241},
     numpages = {13},
     keywords = {Heuristics, Developer Tools, AI Coding Assistants},
     location = { Dubai, United Arab Emirates
     },
     series = {W4A '26},
   }

5. Bespoke Visual Assistance: What and How do Blind and Low-Vision People Create with Agentic Programming?

   Ellie Seehorn, Gene S-H Kim, Aziz Zeidieh, Ather Jammoa, Kunyeul Lee, Aditi Shah, Jaylin Herskovitz, Anhong Guo, and Venkatesh Potluri

   In Proceedings of the 28th International ACM SIGACCESS Conference on Computers and Accessibility, Vila Nova de Gaia, Portugal , 2026

   Abs DOI arXiv Bib Code

   AI-powered assistive technologies have long supported blind and low vision (BLV) people in everyday tasks, but they are general-purpose and often fall short of meeting complex, individualized, in-situ accessibility needs. Though agentic programming tools, like GitHub Copilot, have the potential to bridge this gap by lowering the technical barriers to building personal AT using natural language, the practical applicability of this creation paradigm has been unknown. We address this knowledge gap through a two-phase longitudinal co-design study with five tech-savvy BLV users using ProgramAT, an agentic programming tool that supports the creation, iteration, and testing of camera-based AT. Overall, co-designers created over 37 tools, with some addressing needs unmet by any existing commercial AT such as identifying Uber rides or interpreting hand gestures. Qualitative feedback from our co-designers and analysis of development logs surface BLV strategies for tool creation, along with key challenges including model capability limits, specification conflicts, and barriers to successful creation. We discuss recommendations to provide appropriate conversational scaffolding, community tool sharing capabilities, and support for specialized models and personal datasets for future agentic programming environments to empower BLV users to create bespoke visual assistance for themselves.

   @inproceedings{Seehorn2026BespokeVisualAssistance,
     author = {Seehorn, Ellie and Kim, Gene S-H and Zeidieh, Aziz and Jammoa, Ather and Lee, Kunyeul and Shah, Aditi and Herskovitz, Jaylin and Guo, Anhong and Potluri, Venkatesh},
     title = {Bespoke Visual Assistance: What and How do Blind and Low-Vision People Create with Agentic Programming?},
     year = {2026},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     doi = {10.1145/3797867.3828973},
     isbn = {979-8-4007-2521-0},
     url = {https://doi.org/10.1145/3772318.3791559},
     keywords = {Do-It-Yourself, Generative AI, Visual Assistive Tools, Accessibility},
     booktitle = {Proceedings of the 28th International ACM SIGACCESS Conference on Computers and Accessibility},
     location = {Vila Nova de Gaia, Portugal
     },
   }

6. Reflections and Recommendations on AI Adoption Practice from a Mixed-Ability Research Group

   Shalini Madan, Sreelakshmi Surabiyil Bindu, Veronica Pimenova, Ellie Seehorn, and Venkatesh Potluri

   ASSETS 2026 Experience reports, 2026

   Abs arXiv Bib

   Generative AI tools have recently been rapidly adopted by academics in mixed-ability research teams for both personal and professional tasks. While previous work on adoption of AI-based workflows has focused on collaboration and productivity, the perceptions of AI use within research teams remains divided. Through qualitative analysis of interviews of the five members of our mixed-ability research team, we discuss the motivations, challenges, and practices surrounding the use of generative AI in our lab. We reflect on experiences that shaped recommendations for balanced AI use that enable mixed-ability team workflows: (1) managing disability tax & crip time, (2) homogenizing identity, (3) risk disclosure of private information, (4) self-experimentation and miscellaneous tasks, and (5) information seeking. We build upon these themes to present AI practice recommendations we established for our lab to promote AI workflow adoption while preserving agency and disability identity.

   @article{madan2026reflections,
     title = {Reflections and Recommendations on AI Adoption Practice from a Mixed-Ability Research Group},
     author = {Madan, Shalini and Surabiyil Bindu, Sreelakshmi and Pimenova, Veronica and Seehorn, Ellie and Potluri, Venkatesh},
     journal = {ASSETS 2026 Experience reports},
     year = {2026},
   }

2025

1. MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks

   Kai Nylund, Jennifer Mankoff, and Venkatesh Potluri

   Computer Graphics Forum, 2025

   Abs DOI Bib Code Website

   We present MatplotAlt, an open-source Python package for easily adding alternative text to Matplotlib figures. MatplotAlt equips Jupyter notebook authors to automatically generate and surface chart descriptions with a single line of code or command, and supports a range of options that allow users to customize the generation and display of captions based on their preferences and accessibility needs. Our evaluation indicates that MatplotAlt’s heuristic and LLM-based methods to generate alt text can create accurate long-form descriptions of both simple univariate and complex Matplotlib figures. We find that state-of-the-art LLMs still struggle with factual errors when describing charts, and improve the accuracy of our descriptions by prompting GPT4-turbo with heuristic-based alt text or data tables parsed from the Matplotlib figure.

   @article{Knylund:2025:MatPlotAlt,
     author = {Nylund, Kai and Mankoff, Jennifer and Potluri, Venkatesh},
     title = {MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks},
     journal = {Computer Graphics Forum},
     volume = {44},
     number = {3},
     pages = {e70119},
     doi = {https://doi.org/10.1111/cgf.70119},
     url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/cgf.70119},
     eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.70119},
     year = {2025},
   }

2. Demo of RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People

   Xinyun Cao, Kexin Phyllis Ju, Chenglin Li, Venkatesh Potluri, and Dhruv Jain

   2025

   Abs Bib

   As virtual 3D environments become prevalent, enabling presence and spatial exploration, equitable access is crucial for blind and low-vision (BLV) users.

   @article{caodemo,
     title = {Demo of RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People},
     author = {Cao, Xinyun and Ju, Kexin Phyllis and Li, Chenglin and Potluri, Venkatesh and Jain, Dhruv},
     year = {2025},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
   }

3. Rethinking Productivity with GenAI: A Neurodivergent Students’ Perspective

   Hira Jamshed, Mustafa Naseem, Venkatesh Potluri, and Robin N. Brewer

   In Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility, , 2025

   Abs DOI Bib

   Recent advancements in generative AI (GenAI) leveraging large language models (LLMs) have led to scholarship on how they (e.g., ChatGPT) can help neurodivergent students create customized workarounds and refocus energy. In response to calls for countering ableist narratives of lessening burdens and challenging normative norms that favor neurotypical individuals in prior research, we use interviews (n = 19) to center neurodivergent higher-education students’ accounts related to the use, motivation, and vision for LLM-based GenAI tools in academia. While students found the tools helpful, their experiences revealed challenges with integration into tried-and-tested workflows, limited AI literacy support, experimentation, and flattening personality. Drawing on crip time, we illustrate how GenAI tools can reinforce the normative value of productivity, shifting the burden of access-making onto students themselves. We propose three design values, flexibility, adaptability, and self-authenticity, to reimagine GenAI as a partner rather than a tool prioritizing speed and self-sufficiency.

   @inproceedings{Jamshed2025Rethinking,
     author = {Jamshed, Hira and Naseem, Mustafa and Potluri, Venkatesh and Brewer, Robin N.},
     title = {Rethinking Productivity with GenAI: A Neurodivergent Students' Perspective},
     year = {2025},
     isbn = {9798400706769},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3663547.3746329},
     doi = {10.1145/3663547.3746329},
     booktitle = {Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility},
     articleno = {37},
     numpages = {16},
     keywords = {Generative Artificial Intelligence, Accessibility, Neurodivergence, Disability Studies, Qualitative Research},
     location = {
     },
     series = {ASSETS '25},
   }

2023

1. Notably Inaccessible – Data Driven Understanding of Data Science Notebook (In)Accessibility

   Venkatesh Potluri^*, Sudheesh Singanamalla^*, Firn Tieanklin, and Jennifer Mankoff

   In Proceedings of the 25th International ACM SIGACCESS Conference on Computers and Accessibility, New York, NY, USA, 2023

   * Potluri and Singanamalla contributed equally to this work.

   DOI arXiv Bib Code Website

   @inproceedings{Potluri:2023:Notably-Inaccessible,
     author = {Potluri, Venkatesh and Singanamalla, Sudheesh and Tieanklin, Firn and Mankoff, Jennifer},
     title = {Notably Inaccessible – Data Driven Understanding of Data Science Notebook (In)Accessibility},
     year = {2023},
     isbn = {979-8-4007-0220-4/23/10},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     doi = {10.1145/3597638.3608417},
     booktitle = {Proceedings of the 25th International ACM SIGACCESS Conference on Computers and Accessibility},
     location = {New York, NY, USA},
     series = {ASSETS '23},
     note = {* Potluri and Singanamalla contributed equally to this work.},
   }

2022

1. CodeWalk: Facilitating Shared Awareness in Mixed-Ability Collaborative Software Development

   Venkatesh Potluri^*, Maulishree Pandey^*, Andrew Begel, Michael Barnett, and Scott Reitherman

   In Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility, Athens, Greece, 2022

   * Potluri and Pandey contributed equally to this work.

   DOI Bib

   @inproceedings{potluri:2022:CodeWalk,
     author = {Potluri, Venkatesh and Pandey, Maulishree and Begel, Andrew and Barnett, Michael and Reitherman, Scott},
     title = {{CodeWalk}: Facilitating Shared Awareness in Mixed-Ability Collaborative
                    Software Development},
     year = {2022},
     isbn = {9781450392587},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     doi = {10.1145/3517428.3544812},
     booktitle = {Proceedings of the 24th International ACM SIGACCESS Conference on
                    Computers and Accessibility},
     articleno = {20},
     numpages = {16},
     keywords = {blind or visually impaired, sound effects, collaboration,
                    accessibility, software developers, workspace awareness},
     location = {Athens, Greece},
     series = {ASSETS '22},
     note = {* Potluri and Pandey contributed equally to this work.},
   }

2. PSST: Enabling Blind or Visually Impaired Developers to Author Sonifications of Streaming Sensor Data

   Venkatesh Potluri, John Thompson, James Devine, Bongshin Lee, Nora Morsi, and 3 more authors

   In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, Bend, OR, USA, 2022

   Abs DOI Bib

   We present the first toolkit that equips blind and visually impaired (BVI) developers with the tools to create accessible data displays. Called PSST (Physical computing Streaming Sensor data Toolkit), it enables BVI developers to understand the data generated by sensors from a mouse to a micro:bit physical computing platform. By assuming visual abilities, earlier efforts to make physical computing accessible fail to address the need for BVI developers to access sensor data. PSST enables BVI developers to understand real-time, real-world sensor data by providing control over what should be displayed, as well as when to display and how to display sensor data. PSST supports filtering based on raw or calculated values, highlighting, and transformation of data. Output formats include tonal sonification, nonspeech audio files, speech, and SVGs for laser cutting. We validate PSST through a series of demonstrations and a user study with BVI developers.

   @inproceedings{Potluri:2022:PSST,
     author = {Potluri, Venkatesh and Thompson, John and Devine, James and Lee, Bongshin and Morsi, Nora and De Halleux, Peli and Hodges, Steve and Mankoff, Jennifer},
     title = {{PSST}: Enabling Blind or Visually Impaired Developers to Author
                    Sonifications of Streaming Sensor Data},
     year = {2022},
     isbn = {9781450393201},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     doi = {10.1145/3526113.3545700},
     booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface
                    Software and Technology},
     articleno = {46},
     numpages = {13},
     keywords = {Accessibility, Physical Computing, Toolkit, Blind or Visually Impaired
                    (BVI) Programmers},
     location = {Bend, OR, USA},
     series = {UIST '22},
   }