Anoop K. Sinha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anoop K. Sinha has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- James A. Landay
Stanford University, Stanford, CA, USA
2 shared publications - Shruti Sheth
Google, Mountain View, California, USA
2 shared publications - Adriana Olmos
Google, Montreal, Quebec, Canada
1 shared publication - Alessandro Vinciarelli
University of Glasgow, Glasgow, United Kingdom
1 shared publication - Alex Olwal
Google, United States
1 shared publication - Andrea G. Parker
Google Research, Atlanta, Georgia, USA
1 shared publication
Latest Publications
- Open Access
- 5 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 531-537
Making Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video Player
- 5 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 531-537
Open AccessMaking Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video Player
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1483-1485
Inclusive AI: Rethinking AI-based Multimodal Interaction for Diverse and Underrepresented Users
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1483-1485
Open AccessInclusive AI: Rethinking AI-based Multimodal Interaction for Diverse and Underrepresented Users
- Open Access
- 25 September 2026
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 69 (10) , 38-40
The Multimodal Agent Interfaces Paradigm Shift
How the movement toward multimodal agent interfaces will fundamentally transform users interactions with digital systems.
- 25 September 2026
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 69 (10) , 38-40
Open AccessThe Multimodal Agent Interfaces Paradigm Shift
How the movement toward multimodal agent interfaces will fundamentally transform users interactions with digital systems.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessHuman-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures
- Top Cited PapersOpen Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Prototyping with Prompts: Emerging Approaches and Challenges in Generative AI Design for Collaborative Software Teams
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Top Cited PapersOpen AccessPrototyping with Prompts: Emerging Approaches and Challenges in Generative AI Design for Collaborative Software Teams
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Unanticipated Lessons from Communities: Navigating Society-CenteredResearch in the AI Era
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessUnanticipated Lessons from Communities: Navigating Society-CenteredResearch in the AI Era
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 51-55
Levels of Multimodal Interaction
Large Multimodal Models (LMMs) like OpenAI's GPT4o and Google's Gemini, introduced in 2024, process multiple modalities, enabling significant advances in multimodal interaction. Inspired by frameworks for self-driving cars and AGI, this paper proposes "Levels of Multimodal Interaction" to guide research and development. The four levels are: basic multimodality (0), single modalities in turn-taking; combined multimodality (1), fused interpretation of multiple modalities; humanlike (2), natural interaction flow with additional communication signals; and beyond humanlike (3), surpassing human capabilities and include underlying hidden signals with the potential for transformational human-AI integration. LMMs have progressed from Level 0 to 1, with Level 2 next. Level 3 sets a speculative target that multimodal interaction research could help achieve, where interaction becomes more natural and ultimately surpasses human capabilities. Eventually, such Level 3 multimodal interaction could lead to greater human-AI integration and transform human performance. This anticipated shift, in turn, introduces considerations, particularly around safety, agency and control of AI systems.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 51-55
Open AccessLevels of Multimodal Interaction
Large Multimodal Models (LMMs) like OpenAI's GPT4o and Google's Gemini, introduced in 2024, process multiple modalities, enabling significant advances in multimodal interaction. Inspired by frameworks for self-driving cars and AGI, this paper proposes "Levels of Multimodal Interaction" to guide research and development. The four levels are: basic multimodality (0), single modalities in turn-taking; combined multimodality (1), fused interpretation of multiple modalities; humanlike (2), natural interaction flow with additional communication signals; and beyond humanlike (3), surpassing human capabilities and include underlying hidden signals with the potential for transformational human-AI integration. LMMs have progressed from Level 0 to 1, with Level 2 next. Level 3 sets a speculative target that multimodal interaction research could help achieve, where interaction becomes more natural and ultimately surpasses human capabilities. Eventually, such Level 3 multimodal interaction could lead to greater human-AI integration and transform human performance. This anticipated shift, in turn, introduces considerations, particularly around safety, agency and control of AI systems.
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 78-81
Bespoke: Using LLM agents to generate just-in-time interfaces by reasoning about user intent
Large language models (LLMs) have emerged as a powerful tool for creating personalized knowledge experiences for users, often serving as their own interface through text-based chatbots. The interpretation of user intent and generation of output occur implicitly within the model’s architecture. We propose an alternative approach in a system we call Bespoke where the LLM acts as an agent to explicitly reason about user intent, plan, and generate graphical interfaces to fulfill that intent. This approach enables the creation of visually rich interactions that complement chat-based interactions. By employing a step-by-step reasoning process to reduce ambiguity and keep the model on track, we compose interfaces from a toolkit of widgets, providing a designed and tailored user experience. Our early experiment shows that the output interface differs depending on the interpreted intent. In the current version, these interactions are multimodal in the automatic generation of UI; in future versions, this paradigm can be extended to multiple modalities of input and output. This agentive approach moves the interface towards a personalized, bespoke experience with multimodal interaction that adapts to the user’s intentions. See video demonstration here [2].
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 78-81
Open AccessBespoke: Using LLM agents to generate just-in-time interfaces by reasoning about user intent
Large language models (LLMs) have emerged as a powerful tool for creating personalized knowledge experiences for users, often serving as their own interface through text-based chatbots. The interpretation of user intent and generation of output occur implicitly within the model’s architecture. We propose an alternative approach in a system we call Bespoke where the LLM acts as an agent to explicitly reason about user intent, plan, and generate graphical interfaces to fulfill that intent. This approach enables the creation of visually rich interactions that complement chat-based interactions. By employing a step-by-step reasoning process to reduce ambiguity and keep the model on track, we compose interfaces from a toolkit of widgets, providing a designed and tailored user experience. Our early experiment shows that the output interface differs depending on the interpreted intent. In the current version, these interactions are multimodal in the automatic generation of UI; in future versions, this paradigm can be extended to multiple modalities of input and output. This agentive approach moves the interface towards a personalized, bespoke experience with multimodal interaction that adapts to the user’s intentions. See video demonstration here [2].