CfP: CVPR 2026 Workshop on Interactive Physical AI

We welcome and invite you to participate in the 1st Workshop on Interactive Physical AI. This half-day event will be held at CVPR 2026 in Denver, Colorado in June 2026.  
*****************************************************************
Event: Workshop on Interactive Physical AI 
Location: Denver, Colorado (CVPR 2026) 
3rd or 4th June, 2026
*****************************************************************
Workshop Overview: Interactive Physical AI
Advances in multimodal learning, embodied intelligence, and conversational AI are transforming how humans interact with intelligent AI systems in our physical world. These Interactive Physical AI (IPA) systems can simultaneously perceive humans and scenes with multimodal signals, communicate with verbal and nonverbal behaviors, and act safely and effectively under physical-world constraints in shared spaces. Embodiments of IPA include robots, physically-grounded and environment-aware avatars (e.g., AR telepresence), and on-device audio-visual agents that interact with humans in the physical world. 
This workshop will bring together researchers from computer vision, robotics, and multimodal AI to discuss the full scope of interactive physical AI systems and research challenges to advance this frontier. The program will include invited talks from speakers, as well as posters and spotlight talks of accepted papers. 
Call-for-Papers 
We invite authors to submit unpublished papers (8-page CVPR format) to our workshop, to be presented at a poster session upon acceptance. All submissions will go through a double-blind review process. All contributions must be submitted on OpenReview: https://openreview.net/group?id=thecvf.com/CVPR/2026/Workshop/IPA
Accepted papers will be published in the official CVPR Workshops proceedings and the Computer Vision Foundation (CVF) Open Access archive.
Note: Authors of previously rejected main conference submissions are also welcome to submit their work to our workshop. When doing so, you must submit the previous reviewers' comments (named as previous_reviews.pdf) and a letter of changes (named as letter_of_changes.pdf) as part of your supplementary materials to clearly demonstrate the changes made to address the comments made by previous reviewers.
Topics of interest for papers include, but are not limited to, the following:
  • Human-AI interaction in physical environments
  • Embodied conversational AI and multimodal learning
  • Full-duplex multimodal conversational models
  • Social intelligence and communication for robots and avatars
  • Egocentric vision and first-person perception
  • Real-time audio-visual processing for interactive systems
  • Safe and cooperative human-robot interaction
  • Personalization and lifelong learning for physical AI
  • Privacy-aware learning in interactive settings
  • Physically authentic perception and generation for avatars and agents
Important Dates
  • Deadline: February 28, 2026
  • Notification: March 20, 2026
  • Camera-Ready: April 10, 2026
Organizing Committee
  • Seonwook Park (NVIDIA)
  • Amrita Mazumdar (NVIDIA)
  • Shengze Wang (NVIDIA)
  • Leena Mathur (Carnegie Mellon University) 
  • Koki Nagano (NVIDIA)
  • Shalini De Mello (NVIDIA)
Contact 
If you have any questions about the workshop, please email Seonwook Park at <a id="m_539843564062262161m_8094217301843367980gmail-OWAe84b6fd1-3580-8708-7318-a7e794497756" href="mailto:seonwookp@nvidia.com" title="mailto:seonwookp@nvidia.com” style=”border:0px;font:inherit;margin:0px;padding:0px;vertical-align:baseline” target=”_blank”>seonwookp@nvidia.com
You can leave a response, or trackback from your own site.

Leave a Reply

Design by 2b Consult