EgoCogNav: Cognition-aware Human Egocentric Navigation
ECCV 2026
A multimodal egocentric navigation framework that jointly forecasts human trajectories, head motion and cognitive states from first-person video and multimodal sensory cues.
Zhiwen (Calvin) Qiu
I am a third-year Ph.D. student in Information Science at Cornell University, advised by Saleh Kalantari, with committee members Kuan Fang and Tapomayukh Bhattacharjee. I design embodied systems that perceive, interact, and learn from the physical world for home and assistive robotics, and develop dexterous manipulation platforms for scalable data collection and robot foundation models. Previously, I received a Master of Architecture from UCLA and a B.S. in Architecture from Georgia Tech, and worked as a UX designer at Kuaishou Technology.
News
- Our paper EgoCogNav: Cognition-aware Human Egocentric Navigation is accepted to ECCV 2026.
- I will be starting an internship at Mayo Clinic in Dr. Wei Liu's group, working on an LLM-powered healthcare chatbot and talking-avatar interface for patient-facing education and communication.
- Our paper Designing for Wayfinding in VR: Linking Navigation Interfaces to Spatial Learning and Cognitive Mapping is published at CHI 2026.
- Our systematic review Large Language Model Integrations in Cancer Decision-making is published in npj Digital Medicine.
- Our paper NavMarkAR is accepted to Advanced Engineering Informatics.
Research
Effect-Guided Hierarchical Generation for Stateful Articulated Interaction
In progress
Generates full-body human interaction with articulated objects from language, predicting the intended state change, enforcing it during generation, and verifying the result.
Coming soon
DexTele: Teleoperation with Physics-informed Contact Retargeting for Dexterous Manipulation
In progress
A VR-based teleoperation platform for dexterous manipulation that uses physics-informed contact modeling to gather scalable, high-fidelity training data for robot learning.
Coming soon
Designing for Wayfinding in VR: Linking Navigation Interfaces to Spatial Learning and Cognitive Mapping
CHI 2026
Evaluates the trade-offs in spatial learning, wayfinding performance, cybersickness, and presence of controller-based VR locomotion techniques in virtual indoor environments.
Large Language Model Integrations in Cancer Decision-making: A Systematic Review and Meta-analysis
npj Digital Medicine 2025
A review of 56 studies finds LLMs are used in oncology to summarize and communicate cancer information, but need better clinical readiness, safety evaluation, and datasets for standardized assessment.
NavMarkAR: A Landmark-based Augmented Reality Wayfinding System for Enhancing Older Adults' Spatial Learning
Advanced Engineering Informatics 2024
An AR app that improves older adults' wayfinding efficiency and spatial learning when navigating complex indoor environments.
Other Publications
- Use of Augmented Reality in Human Wayfinding: A Systematic Review
Zhiwen Qiu, Armin Mostafavi, Saleh Kalantari · Virtual Reality 2025
Paper - DentAR: Innovating Dental Visits with Sensory Experiences in AR for People with Autism Spectrum Disorder
Serena Guo, Zhiwen Qiu · CHI Extended Abstracts 2024
Paper - EncoreLife: A Gamified Platform to Enhance Older Adults' Social Connections and Daily Life Structure during Transition to Retirement
Zhiwen Qiu, Hsin-Ming Chao, Mengye Zhu, Chaoyu Wang, Saleh Kalantari · CHI PLAY Companion 2024
Paper · Video
Design
Selected UX and architecture work.
